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. 13323
    Prev
    Next
    INDEX
    Explanations

    information related to individuals' experiences, education, and career history

    oai_token-act-pair · gpt-3.5-turbo

    references to professional roles and achievements

    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
    upid
    -0.85
     sinners
    -0.73
     idiots
    -0.72
    react
    -0.68
     correctness
    -0.67
    sin
    -0.66
     misunderstanding
    -0.66
    bugs
    -0.65
     needles
    -0.65
    rums
    -0.64
    POSITIVE LOGITS
     adjunct
    0.89
     stint
    0.86
     Associate
    0.86
     honorary
    0.85
     volunte
    0.84
     lect
    0.84
     Fellow
    0.82
    ospons
    0.80
     distinguished
    0.80
     advoc
    0.80
    Activations Density 0.543%

    No Known Activations