© 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. 8-RES-JB
    11. 17078
    Prev
    Next
    INDEX
    Explanations

    numerical patterns such as specific digit sequences

    oai_token-act-pair · gpt-3.5-turbo

    quantities and numerical instructions related to items or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sting
    -0.59
     Scourge
    -0.59
     sacked
    -0.59
    bara
    -0.58
    rique
    -0.58
    rame
    -0.58
     Parish
    -0.57
     Beir
    -0.57
     mockery
    -0.56
     erect
    -0.56
    POSITIVE LOGITS
    ÃĹ
    1.01
    %-
    0.99
    mins
    0.98
     mins
    0.97
     consecutive
    0.96
    +
    0.92
     hrs
    0.90
    px
    0.88
    lbs
    0.87
    ¢
    0.87
    Activations Density 0.280%

    No Known Activations