© 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. 10-RES-JB
    11. 17332
    Prev
    Next
    INDEX
    Explanations

    references to bees and activities related to them

    oai_token-act-pair · gpt-3.5-turbo

    references to bees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nikov
    -0.81
    ctica
    -0.77
    ahime
    -0.73
    ional
    -0.70
    ially
    -0.68
    aneous
    -0.67
     VIDEOS
    -0.67
    nice
    -0.64
     Doyle
    -0.64
    uania
    -0.64
    POSITIVE LOGITS
    keeping
    1.27
    keeper
    1.21
    bee
    1.18
    keepers
    1.18
     hive
    1.04
    Bee
    1.04
     bee
    1.00
    bees
    0.99
     larvae
    0.99
     Bee
    0.99
    Activations Density 0.037%

    No Known Activations