© 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. 3-RES-JB
    11. 10703
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events reaching a conclusion or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "settled"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inges
    -0.80
    enic
    -0.75
    saf
    -0.73
    ocalypse
    -0.70
    emonic
    -0.69
    usha
    -0.68
    adder
    -0.68
    irlf
    -0.67
    eway
    -0.67
    writers
    -0.66
    POSITIVE LOGITS
     settling
    0.94
     settle
    0.90
     settles
    0.84
    sett
    0.82
     settled
    0.81
     settlement
    0.74
    holm
    0.68
     ashore
    0.65
    lander
    0.65
     peacefully
    0.63
    Activations Density 0.011%

    No Known Activations