© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 20532
    Prev
    Next
    INDEX
    Explanations

    images and descriptions related to various media formats

    oai_token-act-pair · gpt-3.5-turbo

    references to visual and multimedia elements in various contexts

    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
    route
    -0.73
    sburgh
    -0.72
    factor
    -0.68
    aughs
    -0.68
    upt
    -0.67
     Nadu
    -0.65
    idate
    -0.64
    viron
    -0.64
    oner
    -0.63
     Stability
    -0.63
    POSITIVE LOGITS
     cull
    1.15
     sourced
    1.10
     ranging
    1.02
     from
    1.02
     relating
    1.02
     penned
    1.01
     reminiscent
    0.99
     pertaining
    0.98
     related
    0.97
     inspired
    0.96
    Activations Density 0.321%

    No Known Activations