© 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. 10-RES-JB
    11. 17427
    Prev
    Next
    INDEX
    Explanations

    geographical locations and military actions

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "the" along with contextually significant locations or situations described in a news article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Craft
    -0.88
    geist
    -0.83
    Tesla
    -0.81
    witch
    -0.80
     Wilde
    -0.78
    England
    -0.77
    Opt
    -0.76
    Consumer
    -0.76
    udos
    -0.76
    flix
    -0.75
    POSITIVE LOGITS
     insurgency
    1.29
     Syrian
    1.29
     Kurdish
    1.28
     caliphate
    1.28
     besieged
    1.26
     Iraqi
    1.24
     militants
    1.23
     jihadist
    1.22
     jihadists
    1.20
     Shiite
    1.20
    Activations Density 0.228%

    No Known Activations