© 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. 10-RES-JB
    11. 21698
    Prev
    Next
    INDEX
    Explanations

    information related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    identifiers for specific entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afore
    -0.86
     stead
    -0.71
     inval
    -0.69
     distance
    -0.64
     distances
    -0.63
     unin
    -0.60
     depreciation
    -0.59
     obser
    -0.59
     ostr
    -0.57
     instantaneous
    -0.56
    POSITIVE LOGITS
    ZI
    1.01
    UX
    0.95
    JV
    0.94
    YC
    0.92
    WN
    0.92
    GO
    0.91
    qa
    0.90
    VK
    0.86
    YP
    0.85
    qv
    0.85
    Activations Density 0.029%

    No Known Activations