Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 13342
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases that indicate location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preposition after a comma

    Explanation Uploaded by User

    "in", "to", "for", "as", "with", "during", "having", "try", "you" (after punctuation)

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPA
    -0.58
     wheelchair
    -0.55
    âĢķ
    -0.54
    ,[
    -0.54
    sers
    -0.53
     Legions
    -0.53
     Winged
    -0.52
    —"
    -0.52
     Furious
    -0.52
     {:
    -0.52
    POSITIVE LOGITS
    etheless
    0.84
    asted
    0.68
    morrow
    0.68
    ufact
    0.67
    avis
    0.62
    ailed
    0.62
    Thom
    0.62
    affer
    0.62
     contrad
    0.61
    aples
    0.61
    Activations Density 0.408%

    No Known Activations