© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35395
    Prev
    Next
    INDEX
    Explanations

    relevant locations such as cities and states

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    668
    +0.14
    0.5%
    63
    +0.13
    0.5%
    258
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.14
    224
    +0.13
    0.13
    46
    +0.13
    0.10
    Negative Logits
    Afee
    -0.89
    20439
    -0.83
    LOAD
    -0.72
     seasons
    -0.72
    ufact
    -0.71
    ŃĶ
    -0.70
    Plus
    -0.70
     freedoms
    -0.69
     bumper
    -0.69
    BOOK
    -0.68
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.95
     Territory
    0.90
    jri
    0.89
    quartered
    0.89
    jer
    0.87
     Converted
    0.82
    soDeliveryDate
    0.82
    sylvania
    0.80
     Jed
    0.80
    burgh
    0.79
    Activations Density 8.441%

    No Known Activations