© 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. 22531
    Prev
    Next
    INDEX
    Explanations

    features or amenities in a property or building

    oai_token-act-pair · gpt-3.5-turbo

    lists of features or components related to various subjects

    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
    ¬¼
    -0.78
    ioxide
    -0.77
    ":"/
    -0.76
    OLOG
    -0.75
    erve
    -0.73
    ģĸ
    -0.73
    itone
    -0.72
    ahu
    -0.72
    rio
    -0.71
    ãĤ¢ãĥ«
    -0.71
    POSITIVE LOGITS
     plus
    0.96
     which
    0.92
     including
    0.92
     wherein
    0.85
     whereas
    0.84
     whereby
    0.84
     namely
    0.83
     includ
    0.78
     totaling
    0.75
     although
    0.74
    Activations Density 0.460%

    No Known Activations