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

    Neuronpedia

    Jacobian LensNEW
    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. 24058
    Prev
    Next
    INDEX
    Explanations

    mentions of changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative or significant changes being discussed or implemented

    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
    ographies
    -0.73
    agog
    -0.68
    ãĥ£
    -0.60
     DRAGON
    -0.60
    xious
    -0.57
    Phones
    -0.57
    amina
    -0.57
    ãĥ¥
    -0.56
    ILLE
    -0.56
     Americ
    -0.55
    POSITIVE LOGITS
    uits
    1.01
     wrought
    1.00
    ettings
    0.99
    hips
    0.90
     effected
    0.87
     instituted
    0.84
     thereto
    0.84
    hooting
    0.84
    hops
    0.82
    eatures
    0.81
    Activations Density 0.095%

    No Known Activations