© 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. 1-RES-JB
    6. 13386
    Prev
    Next
    INDEX
    Explanations

    the word "subsequent."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "subsequent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haram
    -0.89
    rod
    -0.88
    Bay
    -0.83
    chest
    -0.78
    mberg
    -0.78
    box
    -0.73
     Sho
    -0.72
     Bee
    -0.72
    neck
    -0.72
    park
    -0.71
    POSITIVE LOGITS
     subsequent
    1.04
    sequent
    1.00
     generations
    0.97
     installments
    0.96
     subsequ
    0.94
     confir
    0.90
     iterations
    0.89
     unsuccessful
    0.89
    etheless
    0.83
    sequently
    0.83
    Activations Density 0.004%

    No Known Activations