© 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. 6683
    Prev
    Next
    INDEX
    Explanations

    phrases related to restructuring or changes

    oai_token-act-pair · gpt-3.5-turbo

    transitional words and phrases that indicate changes or emphasizes points in a discussion

    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
    idated
    -0.48
    sylv
    -0.47
    arsity
    -0.46
    izont
    -0.46
    "}],"
    -0.45
     jewels
    -0.44
     }}
    -0.44
    abl
    -0.44
     ..."
    -0.43
     respectively
    -0.41
    POSITIVE LOGITS
    etheless
    0.80
    resa
    0.78
    odore
    0.72
    xiety
    0.72
    terness
    0.66
    swers
    0.63
    notations
    0.63
    mosp
    0.62
    romeda
    0.62
    nsic
    0.62
    Activations Density 0.889%

    No Known Activations