© 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. 8-RES-JB
    11. 20078
    Prev
    Next
    INDEX
    Explanations

    short phrases indicating the effort or time required to accomplish tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating effort or the need for significant time and resources

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.74
    ADRA
    -0.72
    DM
    -0.72
    achus
    -0.69
    ndra
    -0.66
    oeuv
    -0.66
    tions
    -0.66
    zu
    -0.66
    lished
    -0.65
    arded
    -0.65
    POSITIVE LOGITS
     toll
    1.10
     precedence
    0.85
     wrench
    0.80
     Toll
    0.74
     lot
    0.72
     considerable
    0.69
     bite
    0.67
     aback
    0.67
     huge
    0.66
     disproportionate
    0.65
    Activations Density 0.079%

    No Known Activations