© 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. 2-RES-JB
    11. 14495
    Prev
    Next
    INDEX
    Explanations

    the word "Way" with various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Way" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -0.83
    ĸļ
    -0.80
    uster
    -0.79
     quo
    -0.78
     sugg
    -0.77
     prosec
    -0.73
    ioch
    -0.73
    umbn
    -0.68
    dinand
    -0.67
    usters
    -0.67
    POSITIVE LOGITS
    fare
    1.24
    Way
    1.10
    ward
    1.09
    way
    1.08
    Forward
    0.97
    PASS
    0.92
    point
    0.91
    forward
    0.90
     Forward
    0.89
    finding
    0.89
    Activations Density 0.008%

    No Known Activations