© 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. 1-RES-JB
    11. 24068
    Prev
    Next
    INDEX
    Explanations

    mentions of unemployment or unemployed individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of unemployment and related employment status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arin
    -0.92
    afort
    -0.82
    gran
    -0.82
    ocol
    -0.80
    ebook
    -0.69
    arium
    -0.69
    arta
    -0.68
    agame
    -0.67
    WAYS
    -0.67
    wig
    -0.66
    POSITIVE LOGITS
     unemployed
    1.43
     unemploy
    1.16
     unemployment
    0.99
     Unemployment
    0.91
    employed
    0.84
    uates
    0.81
     suicides
    0.80
    ©¶æ¥µ
    0.78
     workforce
    0.75
     youths
    0.72
    Activations Density 0.010%

    No Known Activations