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. 16435
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confirmation or revelation of information

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of specific events or discoveries

    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
    marg
    -0.87
    istrates
    -0.80
    limits
    -0.73
     responsibilities
    -0.72
     discretion
    -0.70
    ateral
    -0.69
    romy
    -0.69
    imei
    -0.67
     counselors
    -0.67
    uty
    -0.67
    POSITIVE LOGITS
     hoax
    0.98
     fake
    0.87
     indeed
    0.87
     yours
    0.87
     authentic
    0.85
     genuine
    0.83
     theirs
    0.81
     actually
    0.81
     faked
    0.79
     ours
    0.78
    Activations Density 0.533%

    No Known Activations