© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    the term "TL" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to "TL" (top lists or threads) and related content within digital discussions

    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
    eers
    -1.17
    eering
    -1.16
    eer
    -1.04
    xon
    -0.80
    rals
    -0.70
    een
    -0.69
    chester
    -0.69
    Loading
    -0.66
    aan
    -0.66
    better
    -0.65
    POSITIVE LOGITS
    istics
    0.83
    estone
    0.72
    istic
    0.71
    ying
    0.71
    acious
    0.68
    idy
    0.68
    ouse
    0.65
    outing
    0.65
    oiler
    0.64
    istically
    0.64
    Activations Density 0.069%

    No Known Activations