© 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. 7-RES-JB
    11. 13504
    Prev
    Next
    INDEX
    Explanations

    information related to financial matters or economic situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic and societal issues affecting workers and their livelihoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verb
    -0.65
     compliments
    -0.61
    olkien
    -0.57
     evolves
    -0.56
    æĺ¯
    -0.55
     nods
    -0.54
     coincidence
    -0.54
    amorph
    -0.53
     legends
    -0.53
     encour
    -0.52
    POSITIVE LOGITS
     workforce
    0.76
     taxp
    0.72
     affected
    0.68
     sector
    0.66
     industries
    0.66
     stricken
    0.66
     frontline
    0.64
     vulnerable
    0.64
     fragile
    0.63
     remaining
    0.62
    Activations Density 0.974%

    No Known Activations