© 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. 10-RES-JB
    11. 3137
    Prev
    Next
    INDEX
    Explanations

    terms related to actions and events, particularly those involving conflict, creation, discovery, and investigation

    oai_token-act-pair · gpt-3.5-turbo

    references to events or actions occurring in specific places or situations

    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
     helic
    -0.67
    shaw
    -0.58
    acha
    -0.57
    bey
    -0.56
    ffield
    -0.55
     proverb
    -0.55
    liam
    -0.53
    catentry
    -0.52
    ahon
    -0.52
    okingly
    -0.51
    POSITIVE LOGITS
     whatsoever
    1.97
     nor
    1.65
    nor
    1.41
     except
    1.36
     anymore
    1.35
     anywhere
    1.14
     besides
    1.14
     until
    1.11
     unless
    1.11
    soever
    1.05
    Activations Density 0.650%

    No Known Activations