© 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. 1-RES-JB
    11. 24177
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific person or entity, possibly "Cro" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Cro" or related variations

    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
    LESS
    -0.82
    gency
    -0.81
    uate
    -0.75
    raints
    -0.74
    uating
    -0.73
    uyomi
    -0.70
    iary
    -0.70
    UAL
    -0.70
     Nanto
    -0.69
     Werewolf
    -0.69
    POSITIVE LOGITS
     Cro
    1.12
    oked
    1.04
    osph
    0.98
    Cro
    0.95
    cro
    0.88
    chet
    0.85
    tone
    0.82
    tch
    0.81
    agh
    0.81
    lean
    0.80
    Activations Density 0.005%

    No Known Activations