© 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. 12-RES-JB
    11. 4622
    Prev
    Next
    INDEX
    Explanations

    names of individuals or titles with 'Rev' (Reverend)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to religious figures or titles, particularly "Rev" for reverend

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     bould
    -0.59
     sharing
    -0.59
     synd
    -0.59
    holders
    -0.58
     explosives
    -0.56
     spaced
    -0.56
     smelling
    -0.55
     precisely
    -0.55
     quantities
    -0.55
     throats
    -0.55
    POSITIVE LOGITS
    olver
    1.53
    olving
    1.28
    olutions
    1.28
    olt
    1.19
    ital
    1.12
    ivals
    1.10
    isions
    1.09
    ived
    1.07
    lon
    1.04
    ocation
    1.03
    Activations Density 0.023%

    No Known Activations