© 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. 2-RES-JB
    11. 24007
    Prev
    Next
    INDEX
    Explanations

    words related to insects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insects

    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
    xit
    -0.80
    ndum
    -0.75
    NEY
    -0.74
    TABLE
    -0.71
    OA
    -0.71
     Sands
    -0.71
    tg
    -0.70
    CHR
    -0.70
    ndra
    -0.68
    neys
    -0.65
    POSITIVE LOGITS
     pests
    1.16
    icide
    1.07
    icides
    1.07
     insects
    1.05
     larvae
    1.00
     insect
    0.98
    worms
    0.92
    flies
    0.91
     repe
    0.89
    oid
    0.89
    Activations Density 0.012%

    No Known Activations