© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    mentions of death or being dead

    oai_token-act-pair · gpt-3.5-turbo

    references to death or being dead

    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
     CLSID
    -0.66
    yip
    -0.58
    omal
    -0.58
    ECA
    -0.56
     athlet
    -0.55
     Fey
    -0.53
     Perkins
    -0.53
     sugg
    -0.53
    zac
    -0.53
    é¾įå
    -0.53
    POSITIVE LOGITS
    locked
    1.30
    spin
    1.26
    liest
    1.22
    lier
    1.20
    beat
    1.15
    locks
    1.10
    lock
    1.07
    lift
    1.03
    pan
    1.03
    bolt
    1.03
    Activations Density 0.054%

    No Known Activations