© 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. 2-RES-JB
    11. 13671
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving instructions or describing actions

    oai_token-act-pair · gpt-3.5-turbo

    passive constructions and verbs related to actions being performed or questions being addressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARE
    -0.53
    dom
    -0.51
     roots
    -0.50
     Sierra
    -0.49
    issues
    -0.48
    ipeg
    -0.47
    Labor
    -0.47
     axes
    -0.47
    Vers
    -0.47
    insula
    -0.46
    POSITIVE LOGITS
    ĸļ
    0.72
     psychiat
    0.70
     aback
    0.70
    urated
    0.70
    opted
    0.68
    ynamic
    0.66
    Initialized
    0.62
    enced
    0.62
    uled
    0.60
    ãĥĥãĤ¯
    0.59
    Activations Density 0.718%

    No Known Activations