© 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. 2-RES-JB
    11. 17765
    Prev
    Next
    INDEX
    Explanations

    numbers and proper nouns related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations or significant names in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.56
    arius
    -0.53
    Late
    -0.52
    upuncture
    -0.52
    eff
    -0.51
    enance
    -0.51
    rely
    -0.50
    tumblr
    -0.50
    nesday
    -0.50
    ahime
    -0.49
    POSITIVE LOGITS
     Citiz
    0.68
     advoc
    0.62
     cryst
    0.61
     unden
    0.57
     streng
    0.57
     unpop
    0.56
     neigh
    0.55
    ·
    0.55
    ĩ
    0.55
     mathemat
    0.55
    Activations Density 2.412%

    No Known Activations