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. 18363
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and scientific fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various fields of study

    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
     stub
    -0.70
    ATTLE
    -0.69
    ership
    -0.68
     Niet
    -0.66
     TAM
    -0.63
     juicy
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.62
    yond
    -0.61
    cooked
    -0.60
    AUT
    -0.60
    POSITIVE LOGITS
    pace
    1.19
    ilver
    1.14
    mith
    1.05
    uits
    1.04
    hops
    0.96
    hots
    0.93
    henko
    0.93
    heet
    0.92
    cale
    0.92
    hift
    0.91
    Activations Density 0.027%

    No Known Activations