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. 7611
    Prev
    Next
    INDEX
    Explanations

    phrases related to classic things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "classic" in relation to various cultural references and works

    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
    OTUS
    -0.74
    reen
    -0.71
     Simulator
    -0.71
    earcher
    -0.68
    athering
    -0.66
    foreseen
    -0.66
    ttp
    -0.66
    lesh
    -0.65
    heed
    -0.64
    larg
    -0.63
    POSITIVE LOGITS
    arily
    0.98
    isation
    0.73
    ised
    0.72
    marks
    0.69
    osaurs
    0.69
     classics
    0.69
     Revival
    0.69
    isable
    0.69
    icals
    0.69
    ocl
    0.69
    Activations Density 0.015%

    No Known Activations