© 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. 20728
    Prev
    Next
    INDEX
    Explanations

    mentions of archaeological sites

    oai_token-act-pair · gpt-3.5-turbo

    references to archaeological sites

    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
    hest
    -0.75
     Venom
    -0.72
     Fargo
    -0.69
     Thrones
    -0.67
    ulhu
    -0.65
     Freeze
    -0.64
     Parenthood
    -0.63
     Disco
    -0.61
    suit
    -0.60
     Pixie
    -0.60
    POSITIVE LOGITS
    otti
    0.74
    oute
    0.73
    fax
    0.73
    assed
    0.70
    ISTORY
    0.67
    ploma
    0.66
     qualified
    0.66
    ogle
    0.64
    qualified
    0.63
    arty
    0.63
    Activations Density 0.000%

    No Known Activations