© 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. 24053
    Prev
    Next
    INDEX
    Explanations

    words related to fighting or battles

    oai_token-act-pair · gpt-3.5-turbo

    references to "gladiators" or phrases involving gladiatorial themes

    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
    hyde
    -0.87
    TAIN
    -0.86
    DragonMagazine
    -0.77
    OLOGY
    -0.76
    cles
    -0.74
    ÄŁ
    -0.73
    ÃįÃį
    -0.72
    FINEST
    -0.70
    ãĤŃ
    -0.67
    chens
    -0.65
    POSITIVE LOGITS
    itz
    1.10
    amping
    1.03
    ib
    1.00
    itched
    0.99
    ashing
    0.95
    itter
    0.94
    anz
    0.94
    immer
    0.93
    adiator
    0.92
    imm
    0.92
    Activations Density 0.007%

    No Known Activations