© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    phrases related to change and impact

    oai_token-act-pair · gpt-3.5-turbo

    references to significant changes or transformations in various contexts

    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
    ccoli
    -0.75
    thens
    -0.74
    eele
    -0.73
    ngth
    -0.71
    produ
    -0.71
    PU
    -0.71
    tests
    -0.68
     followed
    -0.67
    glas
    -0.66
     exceeds
    -0.65
    POSITIVE LOGITS
     trajectory
    1.18
     wording
    1.17
     course
    1.15
     way
    1.15
     outcome
    1.13
     complexion
    1.09
     definition
    1.08
     direction
    1.06
     paradigm
    1.04
     equation
    1.03
    Activations Density 0.091%

    No Known Activations