© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 8239
    Prev
    Next
    INDEX
    Explanations

    email-related phrases including words like "Invalid Email" or "subscribe."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    52
    +0.12
    0.5%
    409
    +0.12
    0.5%
    582
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.12
    0.02
    689
    +0.12
    0.02
    746
    +0.12
    0.01
    Negative Logits
    utic
    -0.87
     Cth
    -0.81
     droid
    -0.78
     fortun
    -0.78
    ulhu
    -0.77
    illance
    -0.76
    #$#$
    -0.75
     differe
    -0.75
    ollower
    -0.74
     bearings
    -0.74
    POSITIVE LOGITS
     Invalid
    0.83
     Collider
    0.79
    vine
    0.78
    tags
    0.78
    Policy
    0.77
    land
    0.77
     Shelter
    0.77
    nutrition
    0.76
    bell
    0.75
    anova
    0.75
    Activations Density 0.133%

    No Known Activations