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. 443
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions, particularly those related to data processing and software development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and software structure

    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
    •single token firings
    fires strongly on " range" and " font" and " locale"

    No Comments

    Negative Logits
    AFTA
    -0.67
    avorite
    -0.66
     challeng
    -0.66
     Nare
    -0.64
    emale
    -0.63
    lyak
    -0.60
     undermin
    -0.59
     arrang
    -0.58
    vous
    -0.58
     submar
    -0.58
    POSITIVE LOGITS
    ="
    0.88
     ==
    0.83
     =
    0.83
     :=
    0.80
    _
    0.79
    Joined
    0.78
    =\"
    0.76
    Name
    0.76
    ==
    0.76
    Names
    0.75
    Activations Density 0.227%

    No Known Activations