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. 6-RES-JB
    6. 2178
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly ones related to significant events or controversial figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bluntness and references to Osama bin Laden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chrom
    -0.84
    ales
    -0.79
    ois
    -0.78
    ault
    -0.78
    itsu
    -0.78
    vals
    -0.77
    ented
    -0.76
    illard
    -0.76
    uci
    -0.76
    uers
    -0.75
    POSITIVE LOGITS
    lihood
    0.81
    _-
    0.70
     IST
    0.67
    cussion
    0.66
    zza
    0.65
     Bin
    0.64
     blunt
    0.63
     understatement
    0.61
     Osama
    0.60
     deaf
    0.59
    Activations Density 0.076%

    No Known Activations