© 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. 9415
    Prev
    Next
    INDEX
    Explanations

    mentions of directions or locations, particularly related to the Orient region

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and associated terms

    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
    APD
    -0.83
    76561
    -0.80
    isSpecialOrderable
    -0.77
    kson
    -0.73
     msec
    -0.72
    channelAvailability
    -0.70
    sburgh
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
     ABE
    -0.67
    merga
    -0.67
    POSITIVE LOGITS
    osc
    0.85
    elin
    0.84
    eering
    0.80
    voy
    0.78
    alties
    0.75
    ometric
    0.74
    ple
    0.74
    pill
    0.73
    estamp
    0.73
    ect
    0.72
    Activations Density 0.023%

    No Known Activations