© 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. 9-RES-JB
    11. 13286
    Prev
    Next
    INDEX
    Explanations

    instructions or recommendations related to performing tasks sequentially

    oai_token-act-pair · gpt-3.5-turbo

    instructions or actions that emphasize the word "first" or the concept of doing something directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukong
    -0.79
    anty
    -0.67
     Tyr
    -0.61
     relevance
    -0.59
    mosp
    -0.59
     stal
    -0.58
     Bett
    -0.56
     Queens
    -0.55
     Bri
    -0.55
    yers
    -0.55
    POSITIVE LOGITS
    aneously
    1.32
    instead
    0.89
    aneous
    0.79
    without
    0.79
     before
    0.76
     lest
    0.75
     instead
    0.75
     afterwards
    0.72
    ascript
    0.71
     because
    0.70
    Activations Density 0.222%

    No Known Activations