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. 16642
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Texas

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Texas

    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
    theless
    -1.04
    ously
    -0.82
    ãĥĭ
    -0.79
    ogle
    -0.73
    fman
    -0.72
    fter
    -0.70
    ogy
    -0.70
    udic
    -0.70
    umbai
    -0.69
    bler
    -0.68
    POSITIVE LOGITS
     Instruments
    1.21
     Tech
    0.94
     Tribune
    0.94
     Rangers
    0.94
     Ranger
    0.90
     Longh
    0.86
     Chains
    0.84
     Hold
    0.81
     Intermediate
    0.75
    boro
    0.74
    Activations Density 0.031%

    No Known Activations