© 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. 4-RES-JB
    11. 3613
    Prev
    Next
    INDEX
    Explanations

    experiences

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of experiences, particularly those that are positive or engaging

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

    No Comments

    Negative Logits
    laws
    -0.68
     prope
    -0.67
    vous
    -0.66
    cellaneous
    -0.65
     subdiv
    -0.64
    law
    -0.64
     actionGroup
    -0.64
     clot
    -0.63
     annex
    -0.63
     spare
    -0.62
    POSITIVE LOGITS
     Experience
    0.93
     experiences
    0.92
    Experience
    0.91
     experien
    0.90
     experience
    0.85
    ually
    0.82
    iences
    0.80
    IENCE
    0.79
    HAEL
    0.78
    reality
    0.76
    Activations Density 0.028%

    No Known Activations