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

    Neuronpedia

    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. 10-RES-JB
    11. 13980
    Prev
    Next
    INDEX
    Explanations

    words related to negative outcomes or statistics

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with statistics and rates related to health and success

    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
    ©¶æ
    -0.65
    earable
    -0.64
     Came
    -0.63
     Wond
    -0.63
    itars
    -0.61
     Nare
    -0.60
    orporated
    -0.59
    ymm
    -0.59
     hacked
    -0.59
    pecially
    -0.58
    POSITIVE LOGITS
     rate
    1.71
     ratio
    1.65
     rates
    1.56
     ratios
    1.48
     count
    1.47
     percentage
    1.45
    Rate
    1.41
    rate
    1.41
     expectancy
    1.40
     percentages
    1.39
    Activations Density 0.681%

    No Known Activations