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. 4075
    Prev
    Next
    INDEX
    Explanations

    phrases related to "Mind", potentially associated with concepts like psychology, thinking, or strategy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mindanao."

    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
     Mehran
    -0.75
    DIR
    -0.74
    YR
    -0.73
    ATED
    -0.69
    ARDS
    -0.69
    acco
    -0.68
    ARD
    -0.68
    HH
    -0.67
     audible
    -0.67
    EStreamFrame
    -0.67
    POSITIVE LOGITS
    fulness
    1.24
    ful
    1.04
    bender
    1.03
    iac
    0.98
    piece
    0.91
    storms
    0.89
    scape
    0.86
    fully
    0.86
    pieces
    0.83
    lessly
    0.83
    Activations Density 0.014%

    No Known Activations