© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14723
    Prev
    Next
    INDEX
    Explanations

    instances of the word "actual."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to factual accuracy and expectations

    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
    anga
    -0.73
    cler
    -0.65
    meyer
    -0.62
     discour
    -0.60
    anes
    -0.60
    stone
    -0.59
    rine
    -0.59
    stall
    -0.59
     blot
    -0.59
     Murdoch
    -0.58
    POSITIVE LOGITS
    actual
    2.74
     Actual
    2.14
    expected
    1.92
    anticipated
    1.06
    letico
    1.00
    ULTS
    0.96
    sufficient
    0.86
    igible
    0.80
     Runtime
    0.79
     EW
    0.77
    Activations Density 0.038%

    No Known Activations