© 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. 6-RES-JB
    11. 5640
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with a contrast or opposition within a statement

    oai_token-act-pair · gpt-3.5-turbo

    explicit document delimiters or end markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ò
    -0.76
    thood
    -0.74
    icia
    -0.73
    imi
    -0.71
    ornings
    -0.69
    essen
    -0.69
    ESPN
    -0.66
    NB
    -0.66
    atoon
    -0.65
    .''
    -0.65
    POSITIVE LOGITS
     slightest
    1.19
     vast
    1.11
     biggest
    1.09
     majority
    1.08
     latter
    1.08
     strongest
    1.06
     greatest
    1.06
     entire
    1.06
     easiest
    1.00
     aforementioned
    1.00
    Activations Density 0.295%

    No Known Activations