© 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. 3-RES-JB
    11. 15095
    Prev
    Next
    INDEX
    Explanations

    terms related to challenging situations or problems

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "facing" in contexts related to challenges or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucky
    -0.80
    ember
    -0.78
    ary
    -0.75
    roma
    -0.75
    rust
    -0.74
    ifications
    -0.70
    edy
    -0.68
    ater
    -0.67
     entit
    -0.67
    aut
    -0.67
    POSITIVE LOGITS
     faces
    0.97
     Faces
    0.96
     facing
    0.94
     faced
    0.92
     face
    0.90
     Face
    0.79
    FACE
    0.76
    crow
    0.74
    face
    0.73
    faces
    0.71
    Activations Density 0.017%

    No Known Activations