© 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. 10-RES-JB
    11. 5060
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating higher likelihood or prevalence

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating comparative likelihoods or intensities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comings
    -0.85
    psons
    -0.82
    skirts
    -0.80
    acly
    -0.79
    wagen
    -0.78
    ufact
    -0.74
    phia
    -0.70
     Lets
    -0.70
    ancial
    -0.69
    culosis
    -0.68
    POSITIVE LOGITS
     likely
    1.61
     susceptible
    1.46
     prone
    1.43
     vulnerable
    1.28
     prevalent
    1.21
     Likely
    1.19
     resilient
    1.18
    likely
    1.18
     liable
    1.17
     inclined
    1.12
    Activations Density 0.129%

    No Known Activations