© 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. 12495
    Prev
    Next
    INDEX
    Explanations

    general rules, procedures, or standards that are being applied or enforced

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding rules and their applicability

    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
    omes
    -0.70
    osal
    -0.69
    otide
    -0.67
    OGR
    -0.65
    ãĥīãĥ©
    -0.65
    asted
    -0.62
    unks
    -0.62
    ortment
    -0.62
    edes
    -0.61
    cipl
    -0.61
    POSITIVE LOGITS
     applies
    0.85
     apply
    0.80
     GOODMAN
    0.79
     exclusively
    0.77
     sparing
    0.77
     uniformly
    0.75
    ourgeois
    0.72
     unfairly
    0.72
    alties
    0.72
     solely
    0.72
    Activations Density 0.043%

    No Known Activations