© 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. 6-RES-JB
    11. 20286
    Prev
    Next
    INDEX
    Explanations

    countries and specific items or products traded between them

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic and political references related to imports, exports, and commodities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CONCLUS
    -0.76
    ãĥ£
    -0.74
    çĶ°
    -0.73
    ãĥ´
    -0.70
    Sym
    -0.69
    jew
    -0.67
    sbm
    -0.66
    hiro
    -0.65
    -->
    -0.63
    missing
    -0.63
    POSITIVE LOGITS
     coffers
    0.70
     premises
    0.68
     rather
    0.67
     ineligible
    0.67
     instead
    0.66
     anymore
    0.64
     unless
    0.63
     warehouses
    0.63
     via
    0.63
     origin
    0.63
    Activations Density 0.908%

    No Known Activations