© 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. 2-RES-JB
    11. 395
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategic or tactical maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    the word "tactics"

    oai_token-act-pair · gpt-4-turbo

    references to various strategies or methods employed in different 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
    leased
    -0.82
    à
    -0.73
    league
    -0.73
    gur
    -0.71
    val
    -0.68
    reciation
    -0.67
    vals
    -0.65
    ergy
    -0.64
    birth
    -0.63
    Rail
    -0.63
    POSITIVE LOGITS
     tactics
    1.15
     tactic
    0.96
     strategies
    0.88
     tricks
    0.85
     lawy
    0.84
     methods
    0.84
    ategy
    0.84
     techniques
    0.83
     strategy
    0.79
     revers
    0.77
    Activations Density 0.018%

    No Known Activations