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. 10276
    Prev
    Next
    INDEX
    Explanations

    programming code symbols and syntax

    oai_token-act-pair · gpt-3.5-turbo

    symbols and formatting elements commonly found in programming or markup languages

    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
     cle
    -0.67
     travers
    -0.66
     manif
    -0.65
     glac
    -0.65
     Vale
    -0.63
     virginity
    -0.62
     Cind
    -0.62
     Highlands
    -0.62
    pillar
    -0.61
     Walton
    -0.61
    POSITIVE LOGITS
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.89
     SHARES
    0.85
    maxwell
    0.79
    mosp
    0.76
     :=
    0.76
    =#
    0.75
    asionally
    0.74
    anyahu
    0.74
     References
    0.74
    ĻĤ
    0.74
    Activations Density 0.137%

    No Known Activations