© 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. 11-RES-JB
    11. 6919
    Prev
    Next
    INDEX
    Explanations

    headlines or titles of news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newspaper headlines and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enser
    -0.76
    cible
    -0.74
    ajor
    -0.73
    ensis
    -0.70
    ucket
    -0.70
    aryn
    -0.69
    enne
    -0.68
    encia
    -0.68
    ulu
    -0.67
    ignt
    -0.67
    POSITIVE LOGITS
     headline
    1.26
     headlines
    1.25
     proclaiming
    1.02
     announcing
    0.88
     headlined
    0.87
    lined
    0.86
     screamed
    0.77
    LINE
    0.77
     grabbing
    0.76
     omission
    0.76
    Activations Density 0.074%

    No Known Activations