© 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. 7-RES-JB
    11. 20613
    Prev
    Next
    INDEX
    Explanations

    instances where two or more entities come together or collaborate

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "join" 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
     tiss
    -0.68
    intendent
    -0.67
    ester
    -0.65
    framework
    -0.63
    otropic
    -0.62
    bane
    -0.62
    agers
    -0.61
    andi
    -0.61
     amplification
    -0.61
     equival
    -0.60
    POSITIVE LOGITS
     forces
    0.94
     Forces
    0.73
     ranks
    0.71
     hands
    0.68
    itored
    0.68
    TAIN
    0.66
    iton
    0.66
    âĸ¬âĸ¬
    0.66
    ATURES
    0.66
    lift
    0.66
    Activations Density 0.045%

    No Known Activations