© 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. 471
    Prev
    Next
    INDEX
    Explanations

    references to computer programming related to user interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to user-related keywords in a digital context

    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
     cement
    -0.81
     foil
    -0.68
     cav
    -0.68
     mourning
    -0.67
     ang
    -0.67
     nab
    -0.66
     funer
    -0.66
     premier
    -0.65
     booming
    -0.64
     jeans
    -0.64
    POSITIVE LOGITS
     User
    3.14
    User
    2.88
     Users
    2.21
    Users
    1.56
    user
    1.51
    users
    1.41
    USER
    1.41
     Customer
    1.26
     Password
    1.23
     Username
    1.22
    Activations Density 0.024%

    No Known Activations