© 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. 4-RES-JB
    11. 14904
    Prev
    Next
    INDEX
    Explanations

    words related to searching or seeking

    oai_token-act-pair · gpt-3.5-turbo

    the concept of search or searching in various contexts

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

    No Comments

    Negative Logits
    minecraft
    -0.71
    Production
    -0.71
    Downloadha
    -0.71
    ivari
    -0.68
    versions
    -0.66
    noxious
    -0.65
    Morning
    -0.63
    Written
    -0.62
    Donald
    -0.62
    published
    -0.61
    POSITIVE LOGITS
     engines
    0.83
    lights
    0.76
    alogy
    0.76
    alysed
    0.76
    ãĤ¡
    0.71
     warrant
    0.71
    lust
    0.71
    light
    0.70
     sear
    0.70
    VILLE
    0.70
    Activations Density 0.014%

    No Known Activations