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. 13144
    Prev
    Next
    INDEX
    Explanations

    words that indicate an evaluation or assessment of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or subjective impressions

    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
    apsed
    -0.75
    isin
    -0.73
    jac
    -0.71
    keyes
    -0.69
    aredevil
    -0.68
    uve
    -0.68
    pour
    -0.66
    aign
    -0.66
    cot
    -0.66
    gart
    -0.66
    POSITIVE LOGITS
     louder
    0.91
     vaguely
    0.88
     awfully
    0.86
     suspic
    0.83
     like
    0.80
    bite
    0.80
     omin
    0.79
     familiar
    0.79
     snipp
    0.79
     faintly
    0.78
    Activations Density 0.023%

    No Known Activations