© 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. 2-RES-JB
    6. 23210
    Prev
    Next
    INDEX
    Explanations

    references to unspecified individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "bodies" or the concept of "body" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FEC
    -0.69
     Dickens
    -0.68
     liability
    -0.68
     CES
    -0.64
    heny
    -0.62
    ãĢİ
    -0.62
     Gingrich
    -0.61
     precip
    -0.60
     PBS
    -0.60
     Kafka
    -0.59
    POSITIVE LOGITS
    body
    1.13
    guards
    1.09
    bags
    0.96
    bag
    0.87
    anguage
    0.84
    hood
    0.84
    weight
    0.83
    builder
    0.82
    guard
    0.81
    halla
    0.80
    Activations Density 0.008%

    No Known Activations