© 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. 0-RES-JB
    11. 7974
    Prev
    Next
    INDEX
    Explanations

    commands to send information or take action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Send" likely indicating communication or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olics
    -0.74
     mole
    -0.71
    croft
    -0.66
     introduction
    -0.65
     cane
    -0.64
     introdu
    -0.64
     entry
    -0.64
    locks
    -0.63
     Puzzles
    -0.63
     infiltration
    -0.62
    POSITIVE LOGITS
     Send
    2.63
    Send
    1.60
    usat
    1.55
     premature
    1.10
     divorced
    0.91
     deaf
    0.85
     YOU
    0.85
     Cannes
    0.76
    gency
    0.74
     Ni
    0.73
    Activations Density 0.029%

    No Known Activations