© 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. 10-RES-JB
    11. 24521
    Prev
    Next
    INDEX
    Explanations

    geographical locations or names of countries

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and references to international contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.63
    uer
    -0.62
    Accessory
    -0.61
    reement
    -0.59
    isu
    -0.57
    rious
    -0.57
    ãĥ¼ãĥĨãĤ£
    -0.55
     kicker
    -0.53
     looph
    -0.53
     knob
    -0.52
    POSITIVE LOGITS
     alike
    1.73
     respectively
    1.33
     realms
    0.98
     thereafter
    0.96
     contexts
    0.94
     arenas
    0.91
     thereof
    0.89
     versa
    0.88
     sectors
    0.86
     regions
    0.84
    Activations Density 0.361%

    No Known Activations