© 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. 10-RES-JB
    11. 24447
    Prev
    Next
    INDEX
    Explanations

    words related to possibility and likelihood

    oai_token-act-pair · gpt-3.5-turbo

    expressions of possibility or hypotheticals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livest
    -0.79
    ciating
    -0.74
    ļéĨĴ
    -0.65
    usalem
    -0.65
    pes
    -0.64
    options
    -0.64
    ilan
    -0.64
    gins
    -0.64
    rongh
    -0.63
    tesy
    -0.63
    POSITIVE LOGITS
     that
    1.16
     they
    0.92
    that
    0.83
     we
    0.80
     coincidence
    0.79
     THAT
    0.75
     someone
    0.73
     he
    0.73
     she
    0.69
     enough
    0.68
    Activations Density 0.078%

    No Known Activations