© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Murd" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references and mentions of "Murdoch."

    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
    SEC
    -0.65
    FORE
    -0.63
    DCS
    -0.61
    xon
    -0.60
    displayText
    -0.59
     Mn
    -0.58
    phant
    -0.58
     Genie
    -0.56
     Jinping
    -0.55
     Monaco
    -0.55
    POSITIVE LOGITS
    itives
    1.21
    erer
    1.11
    erers
    1.03
    sworth
    0.97
    ezvous
    0.88
    itive
    0.88
    iers
    0.86
    ish
    0.84
    aby
    0.83
    eways
    0.83
    Activations Density 0.045%

    No Known Activations