© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    words related to actions or achievements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to funding, success, learning, and the complexities of relationships in different 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
    idth
    -0.61
     bullish
    -0.59
    resa
    -0.58
     attRot
    -0.57
    arks
    -0.56
     seriousness
    -0.52
    length
    -0.52
    assi
    -0.51
    hur
    -0.50
    eah
    -0.48
    POSITIVE LOGITS
     via
    1.50
     through
    1.42
     indirectly
    1.27
    through
    1.22
    via
    1.15
     thru
    1.14
     by
    1.09
     Through
    1.07
     electronically
    1.04
     using
    1.02
    Activations Density 1.162%

    No Known Activations