© 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. 7-RES-JB
    11. 20597
    Prev
    Next
    INDEX
    Explanations

    instances with the word "likely" and associated verbs that indicate probability or speculation

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and negations regarding likelihood or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purportedly
    -0.84
     supposedly
    -0.81
    ĸļ
    -0.79
     allegedly
    -0.76
     apparently
    -0.75
     evidently
    -0.72
    andise
    -0.66
    igers
    -0.66
     clearly
    -0.65
     reportedly
    -0.63
    POSITIVE LOGITS
     misunder
    0.73
    rist
    0.72
    depending
    0.71
    rosso
    0.69
     underestimated
    0.68
    attering
    0.67
     unnoticed
    0.66
    heading
    0.66
    ulp
    0.66
    hin
    0.66
    Activations Density 0.335%

    No Known Activations