© 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. 8-RES-JB
    11. 2133
    Prev
    Next
    INDEX
    Explanations

    words related to strong negative reactions or expressions of anger

    oai_token-act-pair · gpt-3.5-turbo

    expressions of outrage and outcry in response to various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - anger

    No Comments

    Negative Logits
    NetMessage
    -0.70
    ipeg
    -0.68
     Oss
    -0.65
     Entered
    -0.65
    estone
    -0.65
    Password
    -0.65
     Starg
    -0.63
     glide
    -0.63
    omething
    -0.63
    ession
    -0.62
    POSITIVE LOGITS
    ously
    1.19
     indignation
    0.93
    iously
    0.92
     uproar
    0.83
     against
    0.82
     outcry
    0.80
    storm
    0.80
    storms
    0.79
    rained
    0.78
     outrage
    0.75
    Activations Density 0.062%

    No Known Activations