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. 10-RES-JB
    6. 21309
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by interjections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of realization or emphasis, often introducing statements or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -0.81
    arij
    -0.78
    arov
    -0.75
    resso
    -0.75
    -+-+
    -0.75
    Roaming
    -0.74
    İĭ
    -0.74
    alion
    -0.73
    actionDate
    -0.72
    ascript
    -0.71
    POSITIVE LOGITS
     goodness
    0.97
     heavens
    0.97
     yes
    0.96
     yeah
    0.95
     dear
    0.94
     Merlin
    0.88
     GOD
    0.86
     sorry
    0.85
     wait
    0.85
     god
    0.85
    Activations Density 0.037%

    No Known Activations