© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 2257
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific weeks in political contexts

    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
    ;;;;;;;;;;;;
    -0.75
    ĺħ
    -0.69
     centuries
    -0.67
    idences
    -0.66
    geries
    -0.64
     millennium
    -0.63
     1965
    -0.62
     solves
    -0.62
     emulation
    -0.61
     1997
    -0.60
    POSITIVE LOGITS
     canceled
    1.25
     postponed
    1.24
     announced
    1.24
     rescind
    1.24
     reversed
    1.24
     withdrew
    1.20
     abruptly
    1.20
     retracted
    1.18
     signaled
    1.17
     revoked
    1.15
    Activations Density 0.307%

    No Known Activations