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. 22960
    Prev
    Next
    INDEX
    Explanations

    terms related to schools, education, and academic achievement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic achievements and educational concepts

    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
    DragonMagazine
    -0.82
    ãģ®éŃĶ
    -0.73
    IBLE
    -0.71
    ENSE
    -0.70
    ORED
    -0.70
    DEN
    -0.69
    LECT
    -0.68
    ERC
    -0.67
     deprived
    -0.65
     Gemini
    -0.64
    POSITIVE LOGITS
    izoph
    0.96
    utz
    0.92
     sch
    0.88
    warts
    0.88
    afer
    0.82
    aeper
    0.81
    rupulous
    0.80
    neys
    0.80
    nee
    0.79
    ammers
    0.78
    Activations Density 0.007%

    No Known Activations