© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3896
    Prev
    Next
    INDEX
    Explanations

    political figures and their associated activities or events

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their interactions during state visits

    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
     Anarchy
    -0.78
     gore
    -0.77
     Penalty
    -0.74
     Shotgun
    -0.72
    omaly
    -0.72
    BIP
    -0.72
    punk
    -0.71
     subdivision
    -0.71
     BELOW
    -0.70
    ãĥ¯ãĥ³
    -0.68
    POSITIVE LOGITS
     delegation
    1.25
     Lavrov
    1.21
     ambassadors
    1.20
     deleg
    1.20
     diplomats
    1.20
     guests
    1.15
     envoy
    1.14
     greet
    1.13
    assador
    1.12
     diplomatic
    1.10
    Activations Density 1.061%

    No Known Activations