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. 24118
    Prev
    Next
    INDEX
    Explanations

    phrases related to likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "chances."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    DATA
    -0.87
    Meta
    -0.82
    Nap
    -0.77
    zen
    -0.77
    Cart
    -0.76
    ILE
    -0.75
    atra
    -0.74
    Aust
    -0.73
    Bed
    -0.71
    ruck
    -0.70
    POSITIVE LOGITS
    pring
    0.95
    llor
    0.92
     chances
    0.82
     prospects
    0.78
     Rouhani
    0.78
    hift
    0.77
    ensical
    0.76
    bably
    0.70
    cffff
    0.69
    terness
    0.64
    Activations Density 0.030%

    No Known Activations