© 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. 11847
    Prev
    Next
    INDEX
    Explanations

    references to agricultural activities and interactions with farmers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of farmers and related terms

    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
    raints
    -0.73
    umbn
    -0.72
    bsp
    -0.71
    ifice
    -0.71
     RTX
    -0.68
     Tube
    -0.65
     Protocol
    -0.64
     Lumpur
    -0.63
    ansen
    -0.62
     Pastebin
    -0.61
    POSITIVE LOGITS
     farmer
    1.00
     farmers
    0.93
    folk
    0.87
     labou
    0.86
    grass
    0.83
     farms
    0.82
     farming
    0.81
     growers
    0.80
    fol
    0.80
    Farm
    0.79
    Activations Density 0.036%

    No Known Activations