© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3327
    Prev
    Next
    INDEX
    Explanations

    the special characters 'âĢĶ' in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases or symbols related to emotional or mental states

    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
     commun
    -0.76
    worms
    -0.76
    ieth
    -0.75
    ordinate
    -0.70
    perate
    -0.68
    aimon
    -0.67
    uder
    -0.66
    orts
    -0.66
    itic
    -0.65
    icable
    -0.65
    POSITIVE LOGITS
    ————————
    1.82
    ————
    1.74
    ————————————————
    1.26
    ——
    1.06
    _-
    0.97
    ––
    0.83
    âĢķ
    0.79
     namely
    0.78
     albeit
    0.75
    âĢ¢âĢ¢
    0.72
    Activations Density 0.149%

    No Known Activations