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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14817
    Prev
    Next
    INDEX
    Explanations

    names of organizations or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to the Associated Press

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysis
    -0.85
    gone
    -0.81
    ilk
    -0.80
    ggle
    -0.77
    aneers
    -0.76
    chest
    -0.75
    chal
    -0.73
    tty
    -0.73
    isan
    -0.70
    uble
    -0.69
    POSITIVE LOGITS
     Images
    0.93
     Newsp
    0.89
    Images
    0.85
     Press
    0.80
     newsp
    0.77
     Entertainment
    0.71
    Group
    0.71
    Journal
    0.70
    Media
    0.70
     Advertising
    0.70
    Activations Density 0.010%

    No Known Activations