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. 3-RES-JB
    6. 10212
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or making use of resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tapped" and its variations, often in contexts related to resource allocation or inspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bagg
    -0.74
     Explain
    -0.67
     CAS
    -0.66
    egal
    -0.66
     Hurricanes
    -0.66
    CVE
    -0.66
     Deter
    -0.63
     Ravens
    -0.63
    ============
    -0.61
    birth
    -0.61
    POSITIVE LOGITS
    tap
    0.99
     tapping
    0.96
     taps
    0.93
     tap
    0.92
     tapped
    0.90
    urated
    0.86
    apy
    0.80
    Tap
    0.80
    prise
    0.77
    ioned
    0.76
    Activations Density 0.008%

    No Known Activations