© 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 EvalsExportsAPI 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. 33345
    Prev
    Next
    INDEX
    Explanations

    information related to blog posts, publications, and comments on technical topics like CPUs

    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
    767
    +0.09
    0.5%
    720
    +0.08
    0.4%
    567
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.14
    434
    +0.08
    0.07
    430
    +0.08
    0.17
    Negative Logits
    osponsors
    -0.69
    estinal
    -0.61
    venge
    -0.60
    anza
    -0.57
    resa
    -0.53
    isphere
    -0.53
    artney
    -0.51
     arisen
    -0.51
    zik
    -0.50
     wearer
    -0.50
    POSITIVE LOGITS
    姫
    0.67
     Jun
    0.61
     Feb
    0.58
    BuyableInstoreAndOnline
    0.57
     08
    0.56
     Scrib
    0.54
     Jul
    0.54
     Apr
    0.54
     06
    0.54
    isse
    0.53
    Activations Density 8.116%

    No Known Activations