© 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. 11-RES-JB
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    words related to news headlines starting with the word "There"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there" used as an introductory phrase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprom
    -0.57
    ONSORED
    -0.56
     direct
    -0.52
    ãĥ£
    -0.51
     hydrogen
    -0.50
    SPONSORED
    -0.49
     cerebral
    -0.49
    ointed
    -0.49
     consequence
    -0.49
    oint
    -0.49
    POSITIVE LOGITS
    abouts
    1.10
     are
    0.96
     were
    0.93
    fore
    0.93
    upon
    0.92
     ain
    0.90
     Were
    0.90
     exists
    0.89
     weren
    0.89
    FORE
    0.86
    Activations Density 0.092%

    No Known Activations