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. 0-RES-JB
    6. 22159
    Prev
    Next
    INDEX
    Explanations

    public figures or individuals in authoritative positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of officials or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rank
    -0.68
     gallery
    -0.66
     Hate
    -0.66
     Voice
    -0.65
     commissions
    -0.65
     compliment
    -0.65
     knight
    -0.64
     Ranking
    -0.64
     barr
    -0.63
     translated
    -0.63
    POSITIVE LOGITS
    Officials
    2.23
    Authorities
    1.93
    Investigators
    1.65
    Ross
    1.33
    Prosecutors
    1.26
    Reviewer
    1.17
    Reports
    1.05
    Residents
    1.03
    Attempts
    1.00
    Pont
    0.99
    Activations Density 0.037%

    No Known Activations