© 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. 20794
    Prev
    Next
    INDEX
    Explanations

    mentions of examining, analyzing, or observing different aspects or situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of observational statements or analysis related to various subjects

    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
    icia
    -0.69
    shire
    -0.68
    ooth
    -0.68
    hers
    -0.68
    nb
    -0.65
    Skill
    -0.65
    Bind
    -0.64
    vernight
    -0.63
    eed
    -0.63
     âĵĺ
    -0.62
    POSITIVE LOGITS
     positives
    1.02
     possibilities
    0.83
     negatives
    0.83
    paren
    0.83
     objectively
    0.80
     scoreboard
    0.79
     totality
    0.79
     alternatives
    0.75
     demographics
    0.75
     horizon
    0.73
    Activations Density 0.268%

    No Known Activations