© 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. 2-RES-JB
    11. 17044
    Prev
    Next
    INDEX
    Explanations

    names associated with certain entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    proper names and specific titles, particularly those related to individuals and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acular
    -0.80
    orative
    -0.79
    owicz
    -0.78
    ications
    -0.78
    orius
    -0.75
    uary
    -0.73
    anguage
    -0.72
    uality
    -0.72
    inyl
    -0.70
    Ô
    -0.70
    POSITIVE LOGITS
     Vive
    0.81
    IGH
    0.77
    ISTORY
    0.77
    ttle
    0.70
    wives
    0.70
    HAHA
    0.69
    Stand
    0.69
    ospital
    0.69
     LF
    0.69
     Hoff
    0.67
    Activations Density 0.064%

    No Known Activations