© 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. 9968
    Prev
    Next
    INDEX
    Explanations

    positive statements or news

    oai_token-act-pair · gpt-3.5-turbo

    consistently positive phrases, emphasizing the concept of "good news."

    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
    itsch
    -0.77
    ĸļ
    -0.71
    eters
    -0.69
    TIT
    -0.66
    hler
    -0.63
    ustom
    -0.62
    otte
    -0.62
    replace
    -0.61
    ismo
    -0.61
    framework
    -0.60
    POSITIVE LOGITS
     news
    1.37
     outweigh
    1.01
     thing
    1.01
     fortune
    0.92
    news
    0.90
     stuff
    0.88
     ol
    0.86
     folks
    0.85
     part
    0.83
     vib
    0.82
    Activations Density 0.040%

    No Known Activations