© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 441
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental or institutional initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of programs

    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
    estamp
    -0.77
    inness
    -0.73
    ventus
    -0.71
    stad
    -0.69
    ether
    -0.69
    ioned
    -0.67
    fax
    -0.67
    rez
    -0.65
    stone
    -0.65
     Bale
    -0.64
    POSITIVE LOGITS
     programs
    3.65
     Programs
    2.90
     programmes
    2.70
     program
    2.52
     PROGRAM
    2.04
     Program
    2.01
    program
    2.00
    Program
    1.90
     programming
    1.66
     programme
    1.65
    Activations Density 0.013%

    No Known Activations