© 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. 8-RES-JB
    11. 3105
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a strong emotional or physical sensation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of feelings or comparisons involving the phrase "feel like."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    byn
    -0.81
    earance
    -0.65
    conservancy
    -0.64
    oust
    -0.64
    omen
    -0.63
    ruit
    -0.63
    ais
    -0.63
    pez
    -0.62
    iona
    -0.62
    edient
    -0.62
    POSITIVE LOGITS
     crap
    0.92
     shit
    0.83
    lier
    0.82
     fools
    0.70
     idiots
    0.68
    lihood
    0.67
     invincible
    0.67
    olated
    0.66
     stepping
    0.65
     they
    0.65
    Activations Density 0.032%

    No Known Activations