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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17294
    Prev
    Next
    INDEX
    Explanations

    mentions of regions or continents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'O' in various 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
     Swanson
    -0.66
     Yel
    -0.65
     Dickinson
    -0.62
     Till
    -0.62
     Fiat
    -0.59
     Buckley
    -0.58
     Rudd
    -0.57
     Santos
    -0.57
     Arist
    -0.57
     Rousse
    -0.57
    POSITIVE LOGITS
    ceans
    1.35
    scill
    1.31
    vernight
    1.28
    asis
    1.23
    mbudsman
    1.21
    atmeal
    1.18
    vation
    1.14
    phthal
    1.14
    zzy
    1.06
    ahu
    1.06
    Activations Density 0.031%

    No Known Activations