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. 0-RES-JB
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    positive and negative sentiment associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dudley
    -0.65
     establishment
    -0.63
     pir
    -0.62
     Milton
    -0.62
     McDonald
    -0.61
     Mr
    -0.59
     misinterpret
    -0.57
    key
    -0.57
     Ches
    -0.56
     Government
    -0.56
    POSITIVE LOGITS
    +.
    4.11
    +,
    3.77
    +)
    3.28
    +
    2.48
    +++
    1.73
    ++++
    1.69
    +(
    1.66
    -)
    1.60
    ++
    1.57
    -+
    1.48
    Activations Density 0.012%

    No Known Activations