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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9906
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of devolution or dissolution

    oai_token-act-pair · gpt-3.5-turbo

    references to developmental processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPS
    -0.73
    atton
    -0.66
    atra
    -0.66
     FIGHT
    -0.65
    utenberg
    -0.65
    ttp
    -0.63
     Jill
    -0.62
    OUT
    -0.62
     Kaufman
    -0.62
     Stevens
    -0.62
    POSITIVE LOGITS
    merce
    0.86
    ciating
    0.82
    ities
    0.76
    olved
    0.75
    fecture
    0.73
    lly
    0.72
    ancing
    0.72
    minist
    0.71
    ate
    0.71
    heid
    0.70
    Activations Density 0.024%

    No Known Activations