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. 4-RES-JB
    6. 5902
    Prev
    Next
    INDEX
    Explanations

    descriptive words or phrases indicating a strong sense of need or urgency

    oai_token-act-pair · gpt-3.5-turbo

    expressions of urgent need or desperate situations

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

    No Comments

    Negative Logits
    ences
    -0.85
    essee
    -0.80
    insula
    -0.80
    animous
    -0.72
    arthed
    -0.71
    ence
    -0.71
    arth
    -0.66
     citation
    -0.66
    encer
    -0.66
    ittal
    -0.65
    POSITIVE LOGITS
    ãĥ£
    0.87
    needed
    0.81
     patched
    0.75
     pleas
    0.75
    ãĤ§
    0.73
     needed
    0.73
    phans
    0.71
    ache
    0.71
     fought
    0.70
    ãĤ©
    0.70
    Activations Density 0.011%

    No Known Activations