© 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. 7-RES-JB
    11. 12468
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Den" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behav
    -0.69
    EED
    -0.67
     feats
    -0.67
    mph
    -0.66
     Typh
    -0.61
     setbacks
    -0.61
    ramid
    -0.59
    olicy
    -0.58
    EH
    -0.57
     edited
    -0.56
    POSITIVE LOGITS
    omination
    1.16
    izens
    1.15
    omin
    1.12
    izen
    1.04
    unci
    1.04
    unciation
    1.03
    arius
    0.96
    zel
    0.95
    itus
    0.95
    ocide
    0.92
    Activations Density 0.026%

    No Known Activations