© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of legal or financial entities

    oai_token-act-pair · gpt-3.5-turbo

    references to entities, particularly in a legal or organizational context

    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
    stroke
    -0.83
    geon
    -0.72
    itivity
    -0.65
    isson
    -0.65
    jin
    -0.65
    rose
    -0.64
    hend
    -0.64
    eful
    -0.63
    byss
    -0.62
    PORT
    -0.61
    POSITIVE LOGITS
     entity
    1.00
    ional
    0.85
     entities
    0.78
     controlled
    0.76
     owned
    0.75
     headquartered
    0.75
    chnology
    0.73
    ality
    0.71
    ally
    0.69
     owner
    0.68
    Activations Density 0.028%

    No Known Activations