© 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. 24023
    Prev
    Next
    INDEX
    Explanations

    terms related to searches or seeking information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "search."

    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
    minecraft
    -0.82
    EStreamFrame
    -0.74
    cil
    -0.72
    ivari
    -0.72
     )]
    -0.69
    thus
    -0.68
    noxious
    -0.67
    cised
    -0.65
    signed
    -0.64
    iHUD
    -0.64
    POSITIVE LOGITS
     searches
    1.05
     search
    0.96
     sear
    0.85
     Search
    0.84
    Search
    0.81
     engines
    0.80
     searched
    0.79
     searching
    0.79
     query
    0.75
     queries
    0.74
    Activations Density 0.015%

    No Known Activations