© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17923
    Prev
    Next
    INDEX
    Explanations

    academic titles and research-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of individuals in an academic or professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     needles
    -0.80
     stereotypes
    -0.74
     conformity
    -0.73
     humiliating
    -0.72
     cann
    -0.72
     demoral
    -0.72
     equival
    -0.68
     traumatic
    -0.66
     parameters
    -0.66
     barbar
    -0.65
    POSITIVE LOGITS
     Managing
    0.81
     LLP
    0.78
     MPH
    0.78
     PhD
    0.77
    elaide
    0.76
    CEO
    0.70
     dean
    0.69
    ken
    0.68
    buquerque
    0.68
    enegger
    0.68
    Activations Density 1.001%

    No Known Activations