© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    terms related to targeting and locating objects

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

    references to location or locational contexts

    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
     Dying
    -0.66
     rounding
    -0.60
     Liber
    -0.59
     form
    -0.58
     decades
    -0.58
     reforming
    -0.56
     parity
    -0.56
     hearts
    -0.55
     fantasies
    -0.54
     cle
    -0.54
    POSITIVE LOGITS
    ust
    1.29
    ator
    1.20
    ution
    1.16
    atable
    1.13
    utor
    1.13
    uments
    1.08
    ators
    1.07
    utions
    1.04
    entric
    1.04
    atell
    1.03
    Activations Density 0.038%

    No Known Activations