© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18732
    Prev
    Next
    INDEX
    Explanations

    contractions and auxiliary verbs in sentences

    oai_token-act-pair · gpt-3.5-turbo

    assertions and statements about capabilities or possibilities

    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
    awed
    -0.59
    ology
    -0.58
     PsyNet
    -0.57
    ologically
    -0.57
    ¯¯¯¯¯¯¯¯
    -0.56
     Suppose
    -0.56
    itu
    -0.56
    istor
    -0.55
    apter
    -0.53
    verse
    -0.53
    POSITIVE LOGITS
     also
    2.30
    also
    1.92
     ALSO
    1.72
     furthermore
    1.60
     additionally
    1.60
     moreover
    1.53
     Also
    1.50
    Also
    1.41
     likewise
    1.40
    Additionally
    1.25
    Activations Density 0.868%

    No Known Activations