© 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. 2-RES-JB
    11. 787
    Prev
    Next
    INDEX
    Explanations

    the number "2" as it appears in various contexts

    oai_token-act-pair · gpt-4-turbo

    numerical sequences or references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "2."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -1.04
    awaru
    -0.92
    ãĥ¼ãĥĨ
    -0.75
    amaru
    -0.75
    lehem
    -0.73
     Seym
    -0.71
    mosp
    -0.70
    imaru
    -0.70
    efully
    -0.69
    etz
    -0.68
    POSITIVE LOGITS
    nd
    1.64
    ½
    1.02
    ND
    1.00
    160
    0.92
    155
    0.89
    147
    0.89
     thirds
    0.87
    172
    0.86
    187
    0.86
    200
    0.86
    Activations Density 0.067%

    No Known Activations