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. 9-RES-JB
    6. 21387
    Prev
    Next
    INDEX
    Explanations

    superlatives or qualities indicating excellence or extremity

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives or expressions of extremes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swer
    -0.72
    PLIED
    -0.72
    kins
    -0.69
    unes
    -0.68
    ied
    -0.67
    instead
    -0.67
    olith
    -0.66
    occupied
    -0.65
    leased
    -0.65
    mere
    -0.65
    POSITIVE LOGITS
     ever
    1.03
     EVER
    1.02
    ever
    1.01
     imaginable
    0.92
     turnaround
    0.77
     Ever
    0.77
     single
    0.73
     possible
    0.71
     disparity
    0.69
     peac
    0.68
    Activations Density 0.133%

    No Known Activations