© 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. 1-RES-JB
    11. 9557
    Prev
    Next
    INDEX
    Explanations

    references to negative or critical reactions to certain actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of public backlash or outcry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.91
    ramid
    -0.79
    estones
    -0.79
    estone
    -0.77
    aky
    -0.75
    aple
    -0.74
    ogo
    -0.73
    ramer
    -0.72
    uchin
    -0.70
    glas
    -0.69
    POSITIVE LOGITS
     backlash
    1.35
    lash
    1.03
     fallout
    0.94
     retaliate
    0.86
     outcry
    0.86
     reactions
    0.85
     uproar
    0.83
     reaction
    0.80
     feedback
    0.78
     pandemonium
    0.76
    Activations Density 0.008%

    No Known Activations