© 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. 0-RES-JB
    11. 20331
    Prev
    Next
    INDEX
    Explanations

    keywords related to something being significant, recognizable, or iconic

    oai_token-act-pair · gpt-3.5-turbo

    the term "iconic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icum
    -0.76
     deficiency
    -0.70
    arding
    -0.69
    respond
    -0.66
    pent
    -0.65
     prelim
    -0.64
    win
    -0.64
    men
    -0.64
    oping
    -0.63
    *
    -0.63
    POSITIVE LOGITS
     iconic
    3.29
     legendary
    1.65
     famous
    1.60
     infamous
    1.60
     famed
    1.57
     unforgettable
    1.53
     beloved
    1.44
     revered
    1.44
     majestic
    1.44
     recognizable
    1.41
    Activations Density 0.015%

    No Known Activations