© 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. 4-RES-JB
    11. 19675
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a long way."

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

    No Comments

    Negative Logits
    urated
    -0.68
    è¦ļéĨĴ
    -0.67
    Nation
    -0.65
    administ
    -0.65
    panic
    -0.64
    antha
    -0.63
    oric
    -0.63
    isodes
    -0.63
    grave
    -0.62
    ļéĨĴ
    -0.60
    POSITIVE LOGITS
    fare
    0.89
    WARD
    0.81
    ward
    0.75
    finder
    0.71
    RAY
    0.69
    ------------------------------------------------
    0.69
    ï¸
    0.66
    Äĩ
    0.65
     toward
    0.64
     sanity
    0.63
    Activations Density 0.027%

    No Known Activations