© 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. 2-RES-JB
    11. 23525
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or territorial annexation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to territorial annexation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.71
    pton
    -0.69
    orah
    -0.68
    Sil
    -0.64
    ukemia
    -0.64
     Chimera
    -0.63
    pid
    -0.63
    xious
    -0.61
    acter
    -0.60
    trace
    -0.59
    POSITIVE LOGITS
     annexed
    1.26
     annex
    1.22
     annexation
    1.19
    ãĥ¼ãĥĨãĤ£
    0.86
    uary
    0.79
    itized
    0.79
    ificant
    0.78
    hers
    0.76
    glomer
    0.75
    éĹĺ
    0.75
    Activations Density 0.008%

    No Known Activations