Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14420
    Prev
    Next
    INDEX
    Explanations

    instances of the word "start" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    words related to the action of starting or beginning something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.70
    Dash
    -0.68
     Rothschild
    -0.66
    Property
    -0.66
    ugs
    -0.64
    bey
    -0.64
     Britann
    -0.64
    Scale
    -0.64
    Launch
    -0.62
    dash
    -0.62
    POSITIVE LOGITS
    nesota
    0.78
    ©¶æ
    0.75
     pitchers
    0.73
    viron
    0.73
    rollment
    0.72
     Occupations
    0.71
    igmatic
    0.70
    OURCE
    0.69
    rano
    0.68
    lio
    0.67
    Activations Density 0.031%

    No Known Activations