© 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. 1-RES-JB
    11. 24082
    Prev
    Next
    INDEX
    Explanations

    references to various programs, initiatives, or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various programs, particularly those related to support and social services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icas
    -0.80
    âĵĺ
    -0.74
     castle
    -0.71
     stake
    -0.68
    theless
    -0.67
     statues
    -0.65
    ãĤ¨ãĥ«
    -0.65
    ãĥĸ
    -0.63
    æĢ
    -0.62
     Angels
    -0.62
    POSITIVE LOGITS
    mable
    1.32
     Program
    1.14
    matically
    1.12
    mers
    1.09
    Program
    1.02
    program
    1.02
     Programs
    0.98
    matic
    0.96
    zee
    0.87
     Gutenberg
    0.86
    Activations Density 0.004%

    No Known Activations