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. 11050
    Prev
    Next
    INDEX
    Explanations

    words related to the Jewish faith and culture

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Sep" used as a date reference

    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
    culosis
    -0.98
     tuberculosis
    -0.83
    Reviewer
    -0.76
     Archdemon
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    hyde
    -0.65
    anza
    -0.65
    ngth
    -0.65
     Jackets
    -0.63
     modem
    -0.63
    POSITIVE LOGITS
    arate
    1.15
    aration
    1.10
    ay
    0.95
    aret
    0.92
    ul
    0.85
    rees
    0.84
    ayed
    0.82
    otiation
    0.81
    arat
    0.80
    ú
    0.80
    Activations Density 0.007%

    No Known Activations