© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20167
    Prev
    Next
    INDEX
    Explanations

    references to branding or branded items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to branding and brand identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ippi
    -0.83
    abama
    -0.78
    apeake
    -0.75
    ohyd
    -0.74
    allel
    -0.72
    abet
    -0.72
    vous
    -0.71
    pmwiki
    -0.71
    hap
    -0.70
    etheus
    -0.70
    POSITIVE LOGITS
     branded
    1.41
     branding
    1.18
     brands
    0.94
    branded
    0.89
     loyalty
    0.88
    ovan
    0.87
    wcs
    0.86
    Brand
    0.83
     brand
    0.80
    iate
    0.79
    Activations Density 0.008%

    No Known Activations