© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18680
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of gathering or collecting information or evidence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'gather' in various contexts

    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
    compl
    -0.81
    culus
    -0.80
    infect
    -0.80
    efficient
    -0.79
    coded
    -0.71
    missions
    -0.71
    emb
    -0.71
     colon
    -0.70
    cknow
    -0.70
    incarn
    -0.70
    POSITIVE LOGITS
     gather
    0.99
    ãĥķãĤ¡
    0.96
     Gathering
    0.94
     gathering
    0.93
    ãĤ©
    0.85
    ODY
    0.85
     gathered
    0.83
    è£
    0.79
     gathers
    0.78
     Dickinson
    0.78
    Activations Density 0.009%

    No Known Activations