© 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. 0-RES-JB
    11. 4057
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location, potentially Lah, which may represent Lahore

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or entities, particularly those related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spider
    -0.86
    Spider
    -0.84
    IELD
    -0.75
     Astro
    -0.75
     spider
    -0.74
    DCS
    -0.71
     OU
    -0.70
    ryu
    -0.70
     Marvel
    -0.70
    Psy
    -0.69
    POSITIVE LOGITS
     Lub
    1.86
     Vil
    1.65
     Lah
    1.63
     Lund
    1.61
     Ll
    1.58
     Lars
    1.55
     Lal
    1.51
     Lima
    1.51
    ÅĤ
    1.48
     Lama
    1.45
    Activations Density 0.054%

    No Known Activations