© 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. 1-RES-JB
    6. 20624
    Prev
    Next
    INDEX
    Explanations

    mentions of events or gatherings that involve attending

    oai_token-act-pair · gpt-3.5-turbo

    references to participation in events or meetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    smart
    -0.84
    VER
    -0.63
    deal
    -0.62
    negative
    -0.61
    binary
    -0.61
    cold
    -0.60
    eware
    -0.59
    slice
    -0.59
    problem
    -0.59
    protected
    -0.58
    POSITIVE LOGITS
     Attend
    1.06
     attended
    1.06
     attends
    0.93
     explan
    0.90
     attend
    0.90
     attendance
    0.89
    eret
    0.88
    ivals
    0.83
    uates
    0.82
    ¿½
    0.82
    Activations Density 0.007%

    No Known Activations