© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3200
    Prev
    Next
    INDEX
    Explanations

    references to legal or administrative roles such as 'clerk'

    oai_token-act-pair · gpt-3.5-turbo

    references to clerks in various contexts

    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
     Palestin
    -0.82
     Azerb
    -0.70
    Western
    -0.68
     Afgh
    -0.67
    raid
    -0.67
    risk
    -0.66
     Caucasus
    -0.64
     Tayyip
    -0.63
     fertile
    -0.62
     Indian
    -0.59
    POSITIVE LOGITS
     clerk
    1.22
     clerks
    1.17
     Clerk
    1.12
    wright
    0.78
    zilla
    0.76
    rette
    0.75
     Blaz
    0.74
    ÃŃa
    0.73
    maid
    0.72
    ģĸ
    0.72
    Activations Density 0.015%

    No Known Activations