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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5995
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to characteristics or qualities of objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of essence or authenticity

    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
     confisc
    -0.83
    endix
    -0.83
    ebin
    -0.77
     waivers
    -0.74
    viks
    -0.73
    DoS
    -0.72
    reports
    -0.72
     Examination
    -0.70
    odan
    -0.69
     predictably
    -0.68
    POSITIVE LOGITS
     greatness
    1.02
     individuality
    1.00
     underdog
    0.95
    cellence
    0.93
     masculinity
    0.89
     ethos
    0.84
     excellence
    0.83
     humanity
    0.83
    rio
    0.80
     teamwork
    0.78
    Activations Density 0.785%

    No Known Activations