© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21701
    Prev
    Next
    INDEX
    Explanations

    references to tape, such as tape recorders or tape usage in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tape in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.85
    ationally
    -0.75
    theless
    -0.71
    abad
    -0.68
     Democr
    -0.68
    Ĭ±
    -0.64
    姫
    -0.63
    swer
    -0.63
    nesota
    -0.62
    eous
    -0.60
    POSITIVE LOGITS
     recorder
    1.04
     Tape
    0.98
     tapes
    0.97
     tape
    0.94
    clip
    0.87
    red
    0.86
     cassette
    0.82
     recordings
    0.81
     taped
    0.77
    pered
    0.76
    Activations Density 0.022%

    No Known Activations