© 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. 21193
    Prev
    Next
    INDEX
    Explanations

    the contraction "it's"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 's' 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
     Reef
    -0.83
     Lauder
    -0.64
     Benny
    -0.64
    oop
    -0.62
     GROUP
    -0.58
     POL
    -0.57
     Reporting
    -0.57
    geries
    -0.56
     Compliance
    -0.56
     Polk
    -0.55
    POSITIVE LOGITS
    lightly
    0.72
    forth
    0.68
    agna
    0.67
    theless
    0.66
    udder
    0.63
     selves
    0.60
    self
    0.59
    grim
    0.59
    plete
    0.59
     spoiler
    0.59
    Activations Density 0.287%

    No Known Activations