© 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. 4-RES-JB
    11. 10215
    Prev
    Next
    INDEX
    Explanations

    words related to sudden popularity or fame

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "sensation" and notable figures, particularly in entertainment

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

    No Comments

    Negative Logits
    gotten
    -0.80
    erie
    -0.79
    olan
    -0.77
    giene
    -0.76
    vor
    -0.72
    cium
    -0.72
    estone
    -0.71
    alle
    -0.69
    osta
    -0.69
    atories
    -0.68
    POSITIVE LOGITS
    é¾įåĸļ士
    0.86
    âĺħâĺħ
    0.82
    Winner
    0.81
    çĶ°
    0.73
     FINAL
    0.70
    GREEN
    0.65
    awan
    0.64
    ï¸
    0.63
     novelist
    0.63
    Els
    0.62
    Activations Density 0.024%

    No Known Activations