Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21241
    Prev
    Next
    INDEX
    Explanations

    information related to the technology platform "Azure" by Microsoft

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the cloud service Azure and its associated products

    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
    ulhu
    -0.87
    omas
    -0.85
    ivated
    -0.84
    obe
    -0.84
    ocratic
    -0.83
    uador
    -0.83
    ature
    -0.82
    utations
    -0.81
    astically
    -0.81
    ivation
    -0.80
    POSITIVE LOGITS
    MENTS
    0.81
    flex
    0.77
    Dream
    0.73
     Legion
    0.70
    ments
    0.69
     Dreams
    0.68
    MENT
    0.68
     Swan
    0.68
     Skin
    0.68
    lla
    0.67
    Activations Density 0.041%

    No Known Activations