© 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. 2-RES-JB
    11. 24199
    Prev
    Next
    INDEX
    Explanations

    the word "reaction" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "reaction" and its various forms

    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
    locked
    -0.71
    ffe
    -0.67
     carp
    -0.65
    inav
    -0.64
     Sinai
    -0.63
     sliced
    -0.63
     Flying
    -0.63
    hold
    -0.63
     pil
    -0.63
    ©¶æ
    -0.61
    POSITIVE LOGITS
     reactions
    1.35
     reaction
    1.31
     Reaction
    1.20
    ivation
    1.13
    aries
    1.09
    ivated
    1.02
     responses
    0.93
    ivating
    0.88
    naire
    0.86
    ively
    0.85
    Activations Density 0.015%

    No Known Activations