© 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. 1-RES-JB
    11. 24225
    Prev
    Next
    INDEX
    Explanations

    words related to spawning, such as "spawn," "spawned," and "spawning."

    oai_token-act-pair · gpt-3.5-turbo

    words related to gameplay mechanics involving spawning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thodox
    -0.85
    oric
    -0.75
    asketball
    -0.75
    icho
    -0.72
    ajo
    -0.72
    utherford
    -0.71
    imb
    -0.69
    perty
    -0.68
    atha
    -0.67
    vor
    -0.67
    POSITIVE LOGITS
    Spawn
    1.30
    spawn
    1.14
     spawn
    1.12
     Spawn
    1.12
     spawning
    1.04
     spawned
    1.01
     spawns
    0.96
    ãĥ¼ãĥĨãĤ£
    0.84
    Attach
    0.76
    ãĤ¤ãĥĪ
    0.76
    Activations Density 0.010%

    No Known Activations