© 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. 6-RES-JB
    11. 22010
    Prev
    Next
    INDEX
    Explanations

    names of locations or companies, particularly those containing the word "Cupertino"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or places, particularly involving Apple and its headquarters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.69
     tilt
    -0.66
    enegger
    -0.65
     skew
    -0.64
     enactment
    -0.62
     hypot
    -0.61
     composer
    -0.60
    arcity
    -0.58
    akeru
    -0.57
     onwards
    -0.57
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.89
    igham
    0.83
    idated
    0.81
    ciating
    0.79
    UME
    0.79
    imi
    0.76
    ij士
    0.76
    ãĤ¨ãĥ«
    0.75
    inventoryQuantity
    0.75
    æĦ
    0.73
    Activations Density 0.135%

    No Known Activations