© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24140
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical characteristics and structures, such as color, shape, composition, and patterns

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of colors and visual characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enario
    -0.80
    unker
    -0.78
    peer
    -0.72
    eto
    -0.71
    anship
    -0.70
    urchase
    -0.69
    wagon
    -0.69
    atcher
    -0.68
    awan
    -0.68
    Daily
    -0.68
    POSITIVE LOGITS
     edges
    1.44
     holes
    1.42
     openings
    1.41
     spikes
    1.40
     pores
    1.37
     pillars
    1.37
     electrodes
    1.37
     bumps
    1.36
     wires
    1.35
     seams
    1.34
    Activations Density 0.301%

    No Known Activations