© 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. 6643
    Prev
    Next
    INDEX
    Explanations

    names of specific locations, particularly "Hudson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hudson."

    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
     lapt
    -0.75
     spell
    -0.74
    PLE
    -0.71
    def
    -0.67
     spells
    -0.67
     mage
    -0.66
     blasp
    -0.65
    resh
    -0.64
    %%%%
    -0.64
    cheat
    -0.63
    POSITIVE LOGITS
     Hudson
    4.07
     Thames
    1.41
     Hutchinson
    1.32
     Dawson
    1.21
     Atlantic
    1.21
     Niagara
    1.19
     Harding
    1.18
    Brook
    1.16
     Hoover
    1.15
     Emerson
    1.14
    Activations Density 0.023%

    No Known Activations