© 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. 8-RES-JB
    11. 6462
    Prev
    Next
    INDEX
    Explanations

    words related to location or setting

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases that indicate the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.77
    chairs
    -0.74
    ients
    -0.67
     closes
    -0.63
     didnt
    -0.62
    ples
    -0.62
    imony
    -0.61
    .''.
    -0.59
    players
    -0.58
    ãĢı
    -0.58
    POSITIVE LOGITS
     Glory
    0.71
     another
    0.70
     Carmen
    0.69
    aband
    0.68
     Drift
    0.62
    Sharp
    0.62
     an
    0.61
     Plenty
    0.61
    ports
    0.60
     Sgt
    0.60
    Activations Density 0.105%

    No Known Activations