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. 9-RES-JB
    6. 6233
    Prev
    Next
    INDEX
    Explanations

    terms related to events, contests, software, programs, exhibitions, and funding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contests, campaigns, and software projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemy
    -0.78
    wrong
    -0.78
     Wrong
    -0.78
    farious
    -0.73
    Ĭ±
    -0.73
    omething
    -0.70
    Fake
    -0.69
    angering
    -0.67
     careless
    -0.66
    ween
    -0.66
    POSITIVE LOGITS
     consists
    1.74
     comprises
    1.55
     includes
    1.46
     utilizes
    1.44
     contains
    1.39
     consisted
    1.38
     incorporates
    1.29
     revolves
    1.29
     begins
    1.28
     culmin
    1.27
    Activations Density 0.478%

    No Known Activations