© 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. 4-RES-JB
    11. 3666
    Prev
    Next
    INDEX
    Explanations

    mentions of the former Egyptian President, Hosni Mubarak

    oai_token-act-pair · gpt-3.5-turbo

    references to the former Egyptian President Hosni Mubarak

    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
    ansas
    -0.89
    */(
    -0.84
    ienced
    -0.81
    spin
    -0.77
    bats
    -0.75
    edited
    -0.72
    lessly
    -0.72
    manship
    -0.72
    erous
    -0.71
    inventoryQuantity
    -0.70
    POSITIVE LOGITS
    emi
    0.94
    elsen
    0.90
    zzle
    0.83
    emonic
    0.82
    isance
    0.82
    acs
    0.81
    ptions
    0.81
    ocular
    0.81
    asonic
    0.78
    agara
    0.77
    Activations Density 0.011%

    No Known Activations