© 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. 10700
    Prev
    Next
    INDEX
    Explanations

    phrases related to retracting statements or changing positions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to retracting or reversing previous statements or positions

    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
    ingham
    -0.70
    oven
    -0.69
    electric
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    iop
    -0.64
    Ô
    -0.61
     bloodstream
    -0.60
    maximum
    -0.60
    Ķ
    -0.60
    quality
    -0.59
    POSITIVE LOGITS
     abruptly
    0.89
     sharply
    0.88
     altogether
    0.85
     entirely
    0.82
     considerably
    0.80
    iates
    0.79
     completely
    0.78
     momentarily
    0.78
     decisively
    0.78
     drastically
    0.77
    Activations Density 0.125%

    No Known Activations