© 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. 3-RES-JB
    11. 4138
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal terminology or situations involving law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }.
    -0.66
    SPONSORED
    -0.65
    ]."
    -0.63
     respectively
    -0.63
    )."
    -0.61
    %).
    -0.60
    ]).
    -0.58
    ?).
    -0.58
    ".
    -0.58
    ''.
    -0.58
    POSITIVE LOGITS
     aback
    0.53
    anchester
    0.50
    prisingly
    0.49
    izon
    0.47
     puzzled
    0.46
    berman
    0.46
    :'
    0.46
     differently
    0.45
    enza
    0.44
    allo
    0.44
    Activations Density 3.546%

    No Known Activations