© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    words related to physical surfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "surface."

    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
    agna
    -0.80
    agne
    -0.80
    atto
    -0.76
    alus
    -0.72
    ucky
    -0.70
    ingo
    -0.69
    ija
    -0.69
    avering
    -0.68
    aria
    -0.68
    alid
    -0.68
    POSITIVE LOGITS
    tenance
    0.91
     surface
    0.79
    FACE
    0.77
     cleaners
    0.73
     combatants
    0.70
    Ü
    0.68
    cloth
    0.68
    rences
    0.68
     surfaces
    0.67
    ãĥ¥
    0.66
    Activations Density 0.014%

    No Known Activations