© 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. 8-RES-JB
    6. 18483
    Prev
    Next
    INDEX
    Explanations

    phrases related to places or entities of significance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of media and their contexts, particularly themes and productions

    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
    selves
    -1.06
    nesses
    -0.94
    cies
    -0.74
    sets
    -0.71
    Dialogue
    -0.69
    terness
    -0.68
    vae
    -0.68
    nings
    -0.68
    ness
    -0.67
    nces
    -0.66
    POSITIVE LOGITS
     guiActiveUn
    0.81
     locker
    0.77
    tech
    0.74
     oriented
    0.73
    film
    0.70
    less
    0.69
     boarding
    0.69
    -
    0.69
     grade
    0.66
     skating
    0.65
    Activations Density 0.666%

    No Known Activations