© 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. 9-RES-JB
    11. 15993
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or government actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legislation and industrial development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [&
    -0.69
    ãħĭãħĭ
    -0.65
    ?!"
    -0.64
    )...
    -0.63
     myself
    -0.63
    ?ãĢį
    -0.63
     thereafter
    -0.62
    )</
    -0.61
    )!
    -0.60
     CLSID
    -0.59
    POSITIVE LOGITS
     embattled
    0.73
     taxpayer
    0.68
     lucrative
    0.68
     overseas
    0.67
     secretive
    0.67
     controversial
    0.66
     homegrown
    0.66
     combating
    0.64
     federally
    0.64
     illicit
    0.63
    Activations Density 1.285%

    No Known Activations