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. 4-RES-JB
    6. 2995
    Prev
    Next
    INDEX
    Explanations

    texts describing movement through physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "through."

    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
    SPA
    -0.75
    igh
    -0.69
    arist
    -0.67
    CTV
    -0.67
    rem
    -0.66
    thur
    -0.66
    irst
    -0.66
    TY
    -0.65
    zbollah
    -0.65
    DN
    -0.65
    POSITIVE LOGITS
     Sussex
    0.69
     Portsmouth
    0.69
    through
    0.68
    esville
    0.68
     clenched
    0.67
     Vik
    0.67
     thru
    0.66
     waivers
    0.65
     intersections
    0.64
     Rodrig
    0.63
    Activations Density 0.043%

    No Known Activations