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. 13068
    Prev
    Next
    INDEX
    Explanations

    words related to riddles or complex problems requiring creative thinking

    oai_token-act-pair · gpt-3.5-turbo

    text related to puzzles and puzzle-solving 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
    redits
    -0.74
    oln
    -0.69
    rol
    -0.65
    baugh
    -0.65
     temperatures
    -0.65
    EMP
    -0.64
    ibaba
    -0.64
    redited
    -0.64
    itizen
    -0.64
    estial
    -0.64
    POSITIVE LOGITS
     puzzles
    1.10
     puzzle
    1.09
     solving
    0.94
     Puzzle
    0.93
    ĸļ
    0.86
     solved
    0.85
     Pieces
    0.83
    uzzle
    0.82
     Puzzles
    0.82
     puzz
    0.81
    Activations Density 0.019%

    No Known Activations