Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8414
    Prev
    Next
    INDEX
    Explanations

    instances where a person is asked or encouraged to submit something for review or consideration

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the action of submitting something

    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
     Portug
    -0.71
    ijn
    -0.68
    çİĭ
    -0.65
    hound
    -0.65
    maker
    -0.64
    makers
    -0.62
    gang
    -0.62
    onso
    -0.60
    walker
    -0.60
    enfranch
    -0.60
    POSITIVE LOGITS
    mitted
    0.78
    imens
    0.77
     bids
    0.77
    missions
    0.75
    umbnail
    0.74
     anonymously
    0.73
     petitions
    0.72
     electronically
    0.71
     resumes
    0.71
     submissions
    0.70
    Activations Density 0.059%

    No Known Activations