© 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. 9046
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes mixed with text

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns, particularly those that represent various classifications or categories

    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
    kus
    -0.77
    ovie
    -0.68
     Tanz
    -0.67
     Crescent
    -0.65
    EH
    -0.63
     entreprene
    -0.62
    ndra
    -0.62
    uben
    -0.62
    Laun
    -0.60
     Hoy
    -0.60
    POSITIVE LOGITS
     mismatch
    1.00
     notation
    0.99
     calculation
    0.96
     codes
    0.92
    checks
    0.91
    codes
    0.89
     dictate
    0.88
     requirement
    0.88
    checked
    0.87
     requirements
    0.86
    Activations Density 0.400%

    No Known Activations