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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 12336
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes involving movement or change

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to initiate" or "to start."

    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
    encrypted
    -0.77
    Reviewer
    -0.74
    eway
    -0.74
    oys
    -0.71
    aina
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    gart
    -0.66
     Rated
    -0.63
    taboola
    -0.63
    phies
    -0.62
    POSITIVE LOGITS
    itate
    1.25
    itates
    1.20
    itating
    1.07
    itated
    1.01
    OPLE
    0.82
    lihood
    0.80
    ivated
    0.78
     Canaver
    0.76
    ratom
    0.74
    itant
    0.74
    Activations Density 0.015%

    No Known Activations