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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3348
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Access" and related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Access" and related terms

    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
    stal
    -0.66
    annis
    -0.66
     ejac
    -0.63
     abst
    -0.60
    Lens
    -0.59
     Kern
    -0.59
    tails
    -0.57
    asm
    -0.57
     Fernand
    -0.57
     Investigator
    -0.57
    POSITIVE LOGITS
    ibility
    1.62
    ibly
    1.37
    ible
    1.34
    ory
    1.20
    ibl
    1.17
    ibles
    1.16
    ories
    1.15
    ioned
    1.11
    ibilities
    1.05
    IBLE
    1.05
    Activations Density 0.036%

    No Known Activations