© 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. 2-RES-JB
    11. 4533
    Prev
    Next
    INDEX
    Explanations

    the mention of where someone is originally from

    oai_token-act-pair · gpt-3.5-turbo

    references to 'native' speakers or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATA
    -0.82
    attr
    -0.81
    apego
    -0.78
    ammy
    -0.75
    ATHER
    -0.74
    =-=-=-=-
    -0.74
    ENA
    -0.73
    earchers
    -0.71
    TOP
    -0.70
    eper
    -0.69
    POSITIVE LOGITS
    born
    0.86
     native
    0.85
     americ
    0.77
     Advertisement
    0.74
    spe
    0.73
     Instruments
    0.73
    native
    0.71
    oise
    0.70
     inhabit
    0.69
    izations
    0.69
    Activations Density 0.009%

    No Known Activations