© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15288
    Prev
    Next
    INDEX
    Explanations

    terms related to political advisers or consultants

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political advisory roles

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

    No Comments

    Negative Logits
    awar
    -0.71
    Copyright
    -0.70
    emp
    -0.69
    avery
    -0.67
     Bore
    -0.66
    itans
    -0.64
    Crew
    -0.64
     ransom
    -0.64
    phis
    -0.62
    ±
    -0.61
    POSITIVE LOGITS
     advisor
    1.09
     adviser
    1.07
    ially
    0.99
     advising
    0.97
     advisors
    0.94
     advisers
    0.91
     Advis
    0.91
     Adviser
    0.89
     Advisor
    0.87
     counselor
    0.85
    Activations Density 0.022%

    No Known Activations