© 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. 0-RES-JB
    11. 16569
    Prev
    Next
    INDEX
    Explanations

    locations such as LAPD Headquarters and dates

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation for the Los Angeles Police Department (LAPD)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.70
     prevailing
    -0.70
     Neh
    -0.69
     floors
    -0.67
    atin
    -0.67
     nep
    -0.64
     conversions
    -0.63
     platforms
    -0.63
    terday
    -0.63
     nearest
    -0.62
    POSITIVE LOGITS
     Beard
    0.81
    aucus
    0.76
    LAN
    0.76
    photo
    0.69
     Advertisement
    0.67
    EngineDebug
    0.67
    Configuration
    0.66
    iana
    0.66
    igmatic
    0.66
     stag
    0.66
    Activations Density 0.000%

    No Known Activations