© 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. 14021
    Prev
    Next
    INDEX
    Explanations

    words related to pursuit or chasing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "chase."

    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
    adder
    -0.80
    rogens
    -0.79
    orescent
    -0.72
    aston
    -0.71
    president
    -0.70
    itent
    -0.69
    storage
    -0.69
    raviolet
    -0.68
    emetery
    -0.67
    ighters
    -0.67
    POSITIVE LOGITS
     chase
    1.19
    cade
    0.88
     chasing
    0.88
    eers
    0.83
    hunt
    0.81
    âĸ¬
    0.80
    crow
    0.78
    backs
    0.77
    âĸ¬âĸ¬
    0.74
    ============
    0.73
    Activations Density 0.006%

    No Known Activations