© 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. 10245
    Prev
    Next
    INDEX
    Explanations

    words related to influence or impact

    oai_token-act-pair · gpt-3.5-turbo

    references to themes involving "influence."

    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
    UAL
    -0.81
    BOOK
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    hare
    -0.72
    \\\\\\\\
    -0.69
    Accessory
    -0.66
    soDeliveryDate
    -0.65
     Athletic
    -0.65
    ãģ®éŃĶ
    -0.65
    DragonMagazine
    -0.63
    POSITIVE LOGITS
    inite
    1.30
    luence
    1.26
    rastructure
    1.22
    inity
    1.13
    licted
    1.13
    erno
    1.06
    amous
    1.02
    inf
    1.01
    ractions
    0.99
    urred
    0.99
    Activations Density 0.009%

    No Known Activations