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. 16375
    Prev
    Next
    INDEX
    Explanations

    adjectives related to seriousness or intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severe conditions or situations

    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
    atu
    -0.83
    ynthesis
    -0.81
    xxxxxxxx
    -0.81
    pire
    -0.79
    pires
    -0.78
    ģĸ
    -0.78
    imately
    -0.78
    istry
    -0.76
    ools
    -0.76
    kil
    -0.76
    POSITIVE LOGITS
     shortage
    0.94
     consequences
    0.92
     depressive
    0.91
     penalties
    0.91
     injury
    0.90
     depression
    0.89
     repercussions
    0.88
     traumatic
    0.87
     deterioration
    0.87
     allergic
    0.86
    Activations Density 0.060%

    No Known Activations