© 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. 20387
    Prev
    Next
    INDEX
    Explanations

    verbs related to planning or implications of actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes of change or alteration

    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
    HCR
    -0.73
    kson
    -0.67
    */(
    -0.66
    EStream
    -0.63
    scl
    -0.63
    ãĥĪ
    -0.61
    nas
    -0.61
    ãĤ±
    -0.60
     Gw
    -0.60
    spot
    -0.59
    POSITIVE LOGITS
    aging
    2.80
    age
    2.74
    ages
    2.72
    aged
    2.60
    AGE
    2.31
    agement
    2.25
    agers
    2.10
    AGES
    2.09
    ager
    1.86
    agements
    1.71
    Activations Density 0.113%

    No Known Activations