© 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. 14725
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations such as "IC" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to an entity abbreviated as "IC."

    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
    âķIJâķIJ
    -0.89
    wards
    -0.82
    ãĥī
    -0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    ï¸
    -0.73
    selves
    -0.73
    itism
    -0.73
    shapeshifter
    -0.72
    âĸ¬
    -0.68
    ¶ħ
    -0.66
    POSITIVE LOGITS
    BM
    0.95
    ANN
    0.91
    IJ
    0.86
    trl
    0.84
    overed
    0.82
    omb
    0.81
    ritical
    0.80
    entric
    0.78
    aucas
    0.77
    enna
    0.77
    Activations Density 0.007%

    No Known Activations