© 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. 6757
    Prev
    Next
    INDEX
    Explanations

    mentions of time zones

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific time zone

    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
    flies
    -0.88
    hold
    -0.86
    perse
    -0.77
    ufact
    -0.75
    cle
    -0.70
    cule
    -0.70
    bars
    -0.70
    models
    -0.70
    itability
    -0.69
    bye
    -0.67
    POSITIVE LOGITS
     Cruiser
    0.93
    ypes
    0.92
    EMBER
    0.88
     PT
    0.84
    PD
    0.82
    PT
    0.82
    WS
    0.82
    IME
    0.80
    ECH
    0.79
    TP
    0.78
    Activations Density 0.007%

    No Known Activations