© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3711
    Prev
    Next
    INDEX
    Explanations

    words related to evolution or movement

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     rall
    -0.77
     veter
    -0.71
     purse
    -0.67
     enthusi
    -0.66
     healer
    -0.65
     administrator
    -0.63
     withd
    -0.63
    ury
    -0.62
     independ
    -0.62
     brut
    -0.62
    POSITIVE LOGITS
     [+
    1.14
    jpg
    0.91
     Learns
    0.82
     Continued
    0.81
     Compare
    0.79
    Reviewer
    0.77
     Beware
    0.76
     Photograph
    0.76
     Recommend
    0.75
     Whilst
    0.75
    Activations Density 0.112%

    No Known Activations