© 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. 8-RES-JB
    11. 4603
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Murray" at varying degrees of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Murray."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulatory
    -0.74
    iaries
    -0.74
    ulation
    -0.73
    umper
    -0.72
     skelet
    -0.70
    adian
    -0.69
    reek
    -0.68
    ulate
    -0.68
    alion
    -0.68
    --------------------------------------------------------
    -0.68
    POSITIVE LOGITS
    hoe
    0.76
    wald
    0.76
    cloth
    0.72
    zeb
    0.72
    stein
    0.71
    anyahu
    0.69
    cliffe
    0.68
    hyde
    0.67
    vill
    0.65
    conn
    0.65
    Activations Density 0.032%

    No Known Activations