© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    the word "Bird" with different variations and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Bird."

    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
     stimul
    -0.71
     fentanyl
    -0.71
    jp
    -0.70
     cath
    -0.68
     electroly
    -0.68
     RU
    -0.66
    volt
    -0.66
     Malf
    -0.65
    ctr
    -0.65
    KR
    -0.64
    POSITIVE LOGITS
     Bird
    3.99
    Bird
    3.01
    bird
    2.08
     Birds
    2.04
    birds
    1.65
     bird
    1.57
     birds
    1.25
     pigeon
    1.19
     Hawk
    1.17
     Bee
    1.14
    Activations Density 0.011%

    No Known Activations