© 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. 24191
    Prev
    Next
    INDEX
    Explanations

    instances of the number "2" associated with percentages or quantities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 2 in various contexts

    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
    rolet
    -0.86
    awaru
    -0.85
    etz
    -0.77
    efully
    -0.71
    iership
    -0.70
     Ik
    -0.66
    mosp
    -0.65
    ians
    -0.64
    anasia
    -0.63
    gerald
    -0.63
    POSITIVE LOGITS
    nd
    1.74
    ½
    1.04
    ND
    1.04
    160
    1.00
     thirds
    0.93
    147
    0.93
    187
    0.92
    245
    0.91
    133
    0.90
    222
    0.88
    Activations Density 0.093%

    No Known Activations