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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 24142
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is unnecessary or superfluous

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate something is unnecessary or excessive

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

    No Comments

    Negative Logits
    ammed
    -0.76
    arter
    -0.73
    backed
    -0.73
    roid
    -0.68
    uddy
    -0.62
     negotiated
    -0.61
    odan
    -0.60
    ingle
    -0.60
    rador
    -0.60
    ammad
    -0.59
    POSITIVE LOGITS
    ãĥ©ãĥ³
    0.82
    mares
    0.78
     Osw
    0.75
    entimes
    0.74
    ा
    0.74
    lihood
    0.74
    iously
    0.73
    ortun
    0.72
    uitous
    0.72
    vity
    0.72
    Activations Density 0.013%

    No Known Activations