© 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. 22914
    Prev
    Next
    INDEX
    Explanations

    mentions of close relationships or associations between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" in various contexts

    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
    ICAN
    -0.80
    onso
    -0.71
    AIN
    -0.71
    NZ
    -0.68
     Pengu
    -0.68
     Thieves
    -0.65
    ople
    -0.63
    Sov
    -0.62
    alian
    -0.62
     Lauderdale
    -0.62
    POSITIVE LOGITS
     proximity
    0.92
     minded
    0.90
    sighted
    0.82
     resemblance
    0.81
     confid
    0.81
     shave
    0.80
    liness
    0.80
     confinement
    0.78
     relations
    0.77
     ties
    0.76
    Activations Density 0.032%

    No Known Activations