© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15955
    Prev
    Next
    INDEX
    Explanations

    instances involving a comparison of actions or behaviors against certain standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or ambivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _.
    -0.66
    à¼
    -0.61
    %.
    -0.58
    .$
    -0.57
    $.
    -0.55
     âĢķ
    -0.53
    aca
    -0.52
    ,.
    -0.52
    !,
    -0.52
    ().
    -0.51
    POSITIVE LOGITS
     favourable
    0.55
    ested
    0.55
     adjusting
    0.54
     healed
    0.54
     recovering
    0.51
     parity
    0.51
    uned
    0.51
     recover
    0.51
     acquainted
    0.50
     accountable
    0.49
    Activations Density 1.164%

    No Known Activations