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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23876
    Prev
    Next
    INDEX
    Explanations

    professions or fields that have a broad impact

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to broader contexts or implications

    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
    liest
    -0.77
    girls
    -0.76
    LV
    -0.69
    Guard
    -0.69
    rol
    -0.69
    cru
    -0.67
    anova
    -0.67
    boy
    -0.66
    _-
    -0.65
    Mars
    -0.65
    POSITIVE LOGITS
     than
    0.98
     societal
    0.91
    soType
    0.90
    than
    0.89
     spectrum
    0.89
    izont
    0.84
     scope
    0.84
    sheets
    0.80
     ado
    0.80
     applic
    0.77
    Activations Density 0.017%

    No Known Activations