© 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. 2-RES-JB
    11. 349
    Prev
    Next
    INDEX
    Explanations

    the word "internal" when used to describe something happening within an organization or entity

    oai_token-act-pair · gpt-4-turbo

    keywords related to internal proceedings or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to internal investigations or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.85
    vous
    -0.79
    kers
    -0.76
    Maker
    -0.71
    KI
    -0.70
    ammy
    -0.69
    thouse
    -0.69
    gger
    -0.69
    Recomm
    -0.68
    cloth
    -0.68
    POSITIVE LOGITS
     workings
    1.09
     combustion
    1.07
     organs
    0.95
     affairs
    0.93
    ized
    0.83
     Internal
    0.78
     internal
    0.78
    ization
    0.78
    ised
    0.76
     deliberations
    0.73
    Activations Density 0.010%

    No Known Activations