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

    Neuronpedia

    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. 2-RES-JB
    11. 19074
    Prev
    Next
    INDEX
    Explanations

    references to warriors or combatants

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a 'warrior' in various contexts

    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
    ĸļ
    -0.81
    uate
    -0.78
    orage
    -0.76
    ories
    -0.74
    elong
    -0.73
    upon
    -0.69
    orship
    -0.69
    election
    -0.69
    urate
    -0.68
    choes
    -0.67
    POSITIVE LOGITS
    riors
    1.34
    rior
    1.27
     warrior
    0.91
    llan
    0.89
     warriors
    0.89
     Warrior
    0.87
    ¯¯¯¯
    0.83
    ¯¯¯¯¯¯¯¯
    0.78
    culus
    0.72
    fish
    0.71
    Activations Density 0.012%

    No Known Activations