© 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. 23678
    Prev
    Next
    INDEX
    Explanations

    keywords related to multimedia content sharing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of conjunctions and coordinating words

    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
    ONSORED
    -0.89
    west
    -0.74
    hesda
    -0.72
    EFF
    -0.71
    iola
    -0.70
    ibal
    -0.68
     Loren
    -0.68
    flation
    -0.66
     Ree
    -0.66
    iev
    -0.66
    POSITIVE LOGITS
     videos
    0.91
     Videos
    0.84
     transcripts
    0.81
     video
    0.81
     tapes
    0.79
    ographs
    0.79
     emails
    0.78
     films
    0.78
     presentations
    0.78
     recordings
    0.77
    Activations Density 0.331%

    No Known Activations