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. 15882
    Prev
    Next
    INDEX
    Explanations

    The neuron is focusing on location-based information

    oai_token-act-pair · gpt-3.5-turbo

    instances of questions and inquiries

    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
    zbollah
    -0.69
     Zoro
    -0.63
     occult
    -0.62
     Mao
    -0.60
    etheless
    -0.60
     Neo
    -0.60
    isoft
    -0.59
     EVE
    -0.59
     Manson
    -0.59
     princip
    -0.58
    POSITIVE LOGITS
     Retrieved
    1.04
     (@
    0.84
     Explain
    0.84
    Answer
    0.81
    ?,
    0.80
    Read
    0.77
    ='
    0.74
    Report
    0.74
    >:
    0.73
    @
    0.72
    Activations Density 0.735%

    No Known Activations