© 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. 7-RES-JB
    11. 13353
    Prev
    Next
    INDEX
    Explanations

    email-related terms and requests for information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the provision of information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Modes
    -0.70
    wind
    -0.65
    umblr
    -0.64
     Seas
    -0.63
    doing
    -0.59
    anian
    -0.59
    edIn
    -0.58
    Ta
    -0.58
    indle
    -0.58
     asleep
    -0.57
    POSITIVE LOGITS
    utical
    0.81
    eret
    0.79
     sust
    0.79
     fodder
    0.77
     insight
    0.77
     blueprint
    0.76
     relief
    0.74
     backbone
    0.74
    uggets
    0.72
     reliable
    0.72
    Activations Density 0.182%

    No Known Activations