Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14298
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or community, specifically focusing on "Cu" which could be related to "Cupertino"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Cu" indicating the prefix for a location or reference to Cupertino

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sight
    -0.65
     Progress
    -0.63
    hips
    -0.63
     SPD
    -0.60
     Hawks
    -0.60
    ties
    -0.60
    making
    -0.59
     Alien
    -0.58
    tested
    -0.58
    wagen
    -0.58
    POSITIVE LOGITS
    isine
    1.58
    adr
    1.24
    adra
    1.09
    vette
    1.08
    illin
    1.03
    untu
    1.01
    isin
    1.00
    esta
    1.00
    atro
    0.99
    eto
    0.98
    Activations Density 0.024%

    No Known Activations