© 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. 3-RES-JB
    11. 8249
    Prev
    Next
    INDEX
    Explanations

    words related to requirements or requests

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barkley
    -0.81
    Sham
    -0.79
    dash
    -0.76
     Bulg
    -0.76
     Mayo
    -0.73
     Kuwait
    -0.73
    Ħ¢
    -0.72
     Mongol
    -0.68
     Dollar
    -0.67
     Kazakhstan
    -0.66
    POSITIVE LOGITS
    irement
    1.36
    isitions
    1.35
    isition
    1.32
    irements
    1.30
    encies
    1.21
    ests
    1.17
    iem
    1.12
    iring
    1.07
    requ
    1.03
    ittance
    1.03
    Activations Density 0.019%

    No Known Activations