© 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. 10-RES-JB
    11. 3407
    Prev
    Next
    INDEX
    Explanations

    phrases related to likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    words indicating uncertainty or likelihood

    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
    regate
    -0.85
    iens
    -0.78
    atur
    -0.78
    itiveness
    -0.76
    ukong
    -0.76
    =-=-=-=-=-=-=-=-
    -0.74
    amins
    -0.71
    oir
    -0.71
    ivo
    -0.70
    raq
    -0.70
    POSITIVE LOGITS
     culminating
    1.28
     implying
    1.26
     resulting
    1.24
     indicating
    1.24
     consisting
    1.18
     preferring
    1.18
     involving
    1.16
     requiring
    1.14
     intending
    1.13
     relying
    1.13
    Activations Density 0.122%

    No Known Activations