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. 7-RES-JB
    6. 1057
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helic
    -0.70
    Kit
    -0.69
     bot
    -0.68
     pengu
    -0.66
     Shepherd
    -0.63
     py
    -0.63
     tower
    -0.63
     =================
    -0.62
     Jiu
    -0.61
     Zac
    -0.61
    POSITIVE LOGITS
    tained
    0.95
    ended
    0.90
    arse
    0.87
    ested
    0.86
    assed
    0.85
    opted
    0.84
    arted
    0.84
    tering
    0.84
    akable
    0.83
    urrency
    0.83
    Activations Density 0.224%

    No Known Activations