© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 23751
    Prev
    Next
    INDEX
    Explanations

    phrases related to being first or starting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "First."

    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
     spir
    -0.71
    yne
    -0.64
     supporting
    -0.61
     radi
    -0.60
     toxic
    -0.60
     trails
    -0.59
     under
    -0.59
     sob
    -0.59
     around
    -0.58
     wound
    -0.58
    POSITIVE LOGITS
    First
    3.50
    first
    2.41
    Firstly
    2.41
     First
    2.36
     Firstly
    1.99
    Fourth
    1.87
     FIRST
    1.81
    Second
    1.77
    Third
    1.69
    Secondly
    1.54
    Activations Density 0.011%

    No Known Activations