© 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. 23919
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates or events

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data and references to time frames

    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
     Flavoring
    -0.83
    cius
    -0.76
    ?".
    -0.67
    seless
    -0.64
    existent
    -0.64
     poisons
    -0.64
    Weak
    -0.62
    moral
    -0.61
     vanishing
    -0.61
     resists
    -0.60
    POSITIVE LOGITS
     livestream
    0.99
     streamed
    0.83
     organizers
    0.80
     rollout
    0.74
     simul
    0.73
     reception
    0.72
     updates
    0.69
    updated
    0.68
     booked
    0.68
     organisers
    0.67
    Activations Density 1.193%

    No Known Activations