© 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. 18243
    Prev
    Next
    INDEX
    Explanations

    verbs related to eliciting a response or reaction

    oai_token-act-pair · gpt-3.5-turbo

    words related to evoking or expressing reactions and emotions

    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
     Thou
    -0.67
    amins
    -0.65
    stadt
    -0.64
     Kro
    -0.62
     Bart
    -0.61
     Gamble
    -0.61
    man
    -0.60
     Firm
    -0.60
    hub
    -0.60
     fitt
    -0.60
    POSITIVE LOGITS
     elic
    0.96
    cha
    0.82
    iated
    0.81
    icle
    0.79
    otom
    0.76
     coax
    0.75
    structed
    0.74
    egu
    0.73
    iating
    0.71
    ially
    0.70
    Activations Density 0.027%

    No Known Activations