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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11579
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific male individual in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iculty
    -0.63
    DAY
    -0.61
    Interest
    -0.58
     affiliate
    -0.58
    reshold
    -0.56
    com
    -0.56
    terms
    -0.56
     Articles
    -0.56
     Jindal
    -0.55
    requisite
    -0.55
    POSITIVE LOGITS
    zbollah
    1.21
    resy
    1.04
    'll
    1.03
    reditary
    1.03
     Majesty
    0.96
    uristic
    0.95
    gemony
    0.93
    pherd
    0.92
    eded
    0.91
    aven
    0.91
    Activations Density 0.282%

    No Known Activations