© 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. 1-RES-JB
    11. 21377
    Prev
    Next
    INDEX
    Explanations

    names or titles of political advisors

    oai_token-act-pair · gpt-3.5-turbo

    the presence of individuals in advisory roles, particularly in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Copyright
    -0.73
    flag
    -0.68
    avery
    -0.66
    ±
    -0.66
    ¶ħ
    -0.64
    bra
    -0.63
     Bore
    -0.63
    aver
    -0.63
    Ĺ
    -0.62
    oor
    -0.61
    POSITIVE LOGITS
     adviser
    1.26
     advisor
    1.25
     Adviser
    1.11
     advisers
    1.07
     advisors
    1.03
     counselor
    1.03
     Advis
    1.01
     Advisor
    1.00
     advising
    0.99
     counselors
    0.91
    Activations Density 0.015%

    No Known Activations