© 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. 8-RES-JB
    11. 19393
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and procedures

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to project guidelines and criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĵĺ
    -0.67
    ntil
    -0.64
    ammy
    -0.63
    torn
    -0.58
    pload
    -0.58
    mobi
    -0.58
    amon
    -0.57
    Dub
    -0.56
    asar
    -0.56
    NetMessage
    -0.56
    POSITIVE LOGITS
     sufficiently
    0.86
     reasonably
    0.78
     oneself
    0.74
    /(
    0.70
     beforehand
    0.69
     premise
    0.68
     themselves
    0.67
     physically
    0.67
    psc
    0.67
     adequately
    0.67
    Activations Density 0.815%

    No Known Activations