© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20520
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports teams and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and notable individuals associated with them

    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
     bri
    -0.79
     VIDEOS
    -0.74
    incinnati
    -0.72
     Pike
    -0.72
    annis
    -0.70
     hamb
    -0.70
     Cincinnati
    -0.70
    waukee
    -0.67
    ASH
    -0.67
    ichita
    -0.65
    POSITIVE LOGITS
     Suns
    1.70
     Lama
    1.53
    eties
    1.30
     sill
    1.18
    sight
    1.15
     abort
    1.10
    heed
    1.10
     SDK
    1.07
    rar
    1.04
    etts
    1.04
    Activations Density 0.052%

    No Known Activations