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. 8-RES-JB
    6. 17958
    Prev
    Next
    INDEX
    Explanations

    political representatives and their statements or comments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rep" followed by names, indicating references to representatives or individuals associated with a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.71
    glers
    -0.69
     Brist
    -0.65
    istically
    -0.65
     factor
    -0.64
    phal
    -0.62
     Dwar
    -0.61
     Leap
    -0.60
     trap
    -0.59
    istical
    -0.59
    POSITIVE LOGITS
    orters
    1.48
    rint
    1.31
    orter
    1.27
    orted
    1.26
    ublic
    1.26
    utation
    1.24
    ository
    1.21
    rieve
    1.21
    ositories
    1.18
    atri
    1.16
    Activations Density 0.022%

    No Known Activations