© 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. 0-RES-JB
    11. 2751
    Prev
    Next
    INDEX
    Explanations

    terms related to military or strategic maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayne
    -0.82
     Seal
    -0.80
     Sussex
    -0.76
     Pul
    -0.72
    escal
    -0.72
    edar
    -0.71
     Pug
    -0.70
    fighters
    -0.70
    ultan
    -0.70
     Nano
    -0.68
    POSITIVE LOGITS
     tro
    2.65
     Fra
    1.52
     Vog
    1.25
     Frankfurt
    1.16
    ruck
    1.05
     Erd
    1.05
     repro
    1.00
     ripe
    0.99
     Fors
    0.95
     Mü
    0.94
    Activations Density 0.048%

    No Known Activations