© 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. 0-RES-JB
    6. 22437
    Prev
    Next
    INDEX
    Explanations

    mentions of software or products that target or involve users in various tasks or functions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of users in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anship
    -0.63
    hips
    -0.62
    erey
    -0.62
    ,,
    -0.61
    ship
    -0.61
    ³³³
    -0.61
    vance
    -0.60
     Leh
    -0.60
    bright
    -0.60
     Mour
    -0.59
    POSITIVE LOGITS
     users
    3.58
     Users
    3.04
    users
    2.71
    Users
    2.52
     user
    2.36
     customers
    2.04
     subscribers
    1.95
     consumers
    1.87
    User
    1.86
     User
    1.83
    Activations Density 0.026%

    No Known Activations