© 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. 6739
    Prev
    Next
    INDEX
    Explanations

    questions or prompts requesting information from someone

    oai_token-act-pair · gpt-3.5-turbo

    commands or requests for information

    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
     bracket
    -0.65
    æĪ¦
    -0.64
     disposed
    -0.62
     lacking
    -0.61
     inferior
    -0.60
    acity
    -0.59
     headed
    -0.59
     dash
    -0.59
     exponent
    -0.58
     surplus
    -0.58
    POSITIVE LOGITS
     Tell
    3.73
    Tell
    2.78
    tell
    1.85
     Explain
    1.82
     tell
    1.51
     Desc
    1.43
     Speak
    1.26
     Ask
    1.24
     Say
    1.22
     Write
    1.20
    Activations Density 0.010%

    No Known Activations