© 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. 24137
    Prev
    Next
    INDEX
    Explanations

    words related to enthusiasm or eagerness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "eager."

    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
    anuts
    -0.71
    ammy
    -0.67
    raped
    -0.67
     Surv
    -0.67
    ffen
    -0.66
    hemat
    -0.66
    abases
    -0.65
    onyms
    -0.65
    agram
    -0.63
    stood
    -0.63
    POSITIVE LOGITS
    ness
    1.15
     eager
    1.00
    eful
    0.84
     onlook
    0.81
     eagerly
    0.76
     appet
    0.75
    nesses
    0.74
     appetite
    0.73
     anticipation
    0.69
     thirst
    0.69
    Activations Density 0.009%

    No Known Activations