© 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. 20196
    Prev
    Next
    INDEX
    Explanations

    verbs related to the beginning or initiation of actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "starts" indicating the beginning of various actions or events

    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
    illard
    -0.83
    itech
    -0.76
    rone
    -0.75
    ath
    -0.75
    ickson
    -0.73
    aths
    -0.73
    agon
    -0.69
    yond
    -0.68
    scape
    -0.68
    ye
    -0.67
    POSITIVE LOGITS
    omething
    0.77
     Starts
    0.76
     anew
    0.76
    =-=-
    0.73
    terness
    0.70
    NetMessage
    0.69
     ................
    0.68
    pace
    0.67
    ilver
    0.67
     BELOW
    0.67
    Activations Density 0.015%

    No Known Activations