© 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. 7-RES-JB
    11. 8660
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location - Heathrow airport

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, particularly "Heath."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.79
    ãģ®éŃĶ
    -0.75
    aution
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    edo
    -0.70
    uations
    -0.70
    ual
    -0.68
    eers
    -0.68
    entary
    -0.68
    ents
    -0.68
    POSITIVE LOGITS
    ocratic
    0.89
    lehem
    0.84
    ulhu
    0.72
    ocrat
    0.70
    azar
    0.70
    ought
    0.69
     voyage
    0.69
    rax
    0.68
    opter
    0.68
    reads
    0.66
    Activations Density 0.082%

    No Known Activations