© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23665
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the location "Makati" followed by various contextual information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific geographical location, particularly "Mak" and its variants

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

    No Comments

    Negative Logits
     Reaper
    -1.03
    é¾įå¥ij士
    -0.82
    IDER
    -0.80
    PsyNetMessage
    -0.80
    ãĥ¯ãĥ³
    -0.73
    é¾įåĸļ士
    -0.71
    æĺ¯
    -0.71
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    VEL
    -0.66
    士
    -0.65
    POSITIVE LOGITS
    arov
    1.14
    imura
    0.99
    insk
    0.94
    ati
    0.93
    wana
    0.91
    arak
    0.89
    imir
    0.89
    ihara
    0.88
    owski
    0.87
    ita
    0.87
    Activations Density 0.007%

    No Known Activations