© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 5113
    Prev
    Next
    INDEX
    Explanations

    words expressing likelihood or assumptions

    oai_token-act-pair · gpt-3.5-turbo

    the word "presumably" and its variations, indicating uncertainty or assumption regarding statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ament
    -0.80
    aments
    -0.72
    atures
    -0.70
    Eva
    -0.70
    DER
    -0.69
    bara
    -0.69
    ching
    -0.67
    uese
    -0.67
    enko
    -0.67
    gar
    -0.67
    POSITIVE LOGITS
    æ³
    0.71
    ãĥ¼ãĥĨãĤ£
    0.69
     infer
    0.68
     compens
    0.67
     entail
    0.66
     accommod
    0.66
     implying
    0.66
     unchanged
    0.66
     unsurprisingly
    0.66
    ©¶æ
    0.65
    Activations Density 0.009%

    No Known Activations