© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 5509
    Prev
    Next
    INDEX
    Explanations

    words related to people such as names and roles

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their relationships or roles in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.66
    range
    -0.63
     LIA
    -0.63
    Clear
    -0.63
     Restrict
    -0.62
     TOTAL
    -0.62
    ELF
    -0.61
    vert
    -0.59
    These
    -0.59
     Sovere
    -0.59
    POSITIVE LOGITS
     vou
    1.39
     congratulated
    1.33
     echoed
    1.29
     intervened
    1.20
     joked
    1.20
     remembers
    1.19
     remarked
    1.18
     praised
    1.16
     likewise
    1.15
     admired
    1.14
    Activations Density 0.508%

    No Known Activations