© 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. 2202
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies or policy proposals

    oai_token-act-pair · gpt-3.5-turbo

    references to policy-related topics and 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
     Stain
    -0.75
    upon
    -0.73
    ITNESS
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
     Templ
    -0.69
    hma
    -0.69
    FORMATION
    -0.66
    batch
    -0.66
    ymes
    -0.65
    apy
    -0.65
    POSITIVE LOGITS
     makers
    1.02
     prescriptions
    1.01
    making
    0.96
     advisors
    0.91
    makers
    0.91
     initiatives
    0.89
     policy
    0.89
     interventions
    0.88
     advisers
    0.88
     advisor
    0.88
    Activations Density 0.035%

    No Known Activations