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. 16689
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs indicating a slight degree or amount of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "slightly" and its variations

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

    "slightly"

    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
     Aviv
    -0.80
    elsen
    -0.76
    uments
    -0.76
    iens
    -0.72
    velt
    -0.72
    emy
    -0.72
    yers
    -0.71
    ravings
    -0.69
    rite
    -0.68
    front
    -0.65
    POSITIVE LOGITS
     overlap
    0.77
     offset
    0.74
     tang
    0.73
     earthqu
    0.73
     exaggeration
    0.71
     disagree
    0.69
     incl
    0.68
     overlapping
    0.68
     eccentric
    0.68
    aditional
    0.67
    Activations Density 0.022%

    No Known Activations