© 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. 20284
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and computational symbols

    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
     reluct
    -0.73
     Frankfurt
    -0.73
     CRA
    -0.73
     agre
    -0.72
     PASS
    -0.71
     arri
    -0.70
     Franch
    -0.69
     Bennett
    -0.69
     Cantor
    -0.69
     CARE
    -0.67
    POSITIVE LOGITS
    x
    1.94
    xs
    1.50
    xa
    1.43
    xc
    1.37
    xf
    1.37
    xb
    1.36
    xd
    1.35
    xes
    1.35
    xff
    1.34
    ÃĹ
    1.32
    Activations Density 0.080%

    No Known Activations