© 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. 9-RES-JB
    11. 5335
    Prev
    Next
    INDEX
    Explanations

    words related to particular organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Kurdistan Regional Government and related entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ily
    -0.88
    mes
    -0.83
    estate
    -0.79
    ming
    -0.79
    iminary
    -0.77
    mble
    -0.75
    mont
    -0.75
    afort
    -0.75
    med
    -0.74
    flies
    -0.74
    POSITIVE LOGITS
     Haram
    1.00
    LAND
    0.74
    JV
    0.73
    essed
    0.72
    AME
    0.72
    essional
    0.71
     Kirin
    0.69
    utions
    0.68
    esses
    0.68
    ition
    0.68
    Activations Density 0.191%

    No Known Activations