© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5112
    Prev
    Next
    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    mentions of the letter 'A' in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     outl
    -0.65
     occupations
    -0.63
     lore
    -0.62
     subconscious
    -0.62
     alright
    -0.61
     arcs
    -0.61
     unlock
    -0.60
     partnering
    -0.59
     succeeding
    -0.58
     Nicaragua
    -0.57
    POSITIVE LOGITS
    afia
    1.19
    gha
    1.16
    ksh
    1.16
    ylan
    1.12
    chin
    1.05
    rak
    1.05
    rup
    1.03
    isha
    1.02
    kay
    1.02
    yes
    1.01
    Activations Density 0.036%

    No Known Activations