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. 15344
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons of quantities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and dollar amounts related to quantities or statistics

    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
    ento
    -0.78
    etsy
    -0.77
    oking
    -0.75
    oke
    -0.71
    kefeller
    -0.69
    wright
    -0.68
    PART
    -0.68
    everything
    -0.66
    tel
    -0.66
    ertodd
    -0.65
    POSITIVE LOGITS
     penchant
    0.96
     insistence
    0.93
     inability
    0.92
     maiden
    0.91
     infamous
    0.90
     reluctance
    0.85
     playbook
    0.83
     unwillingness
    0.83
     own
    0.82
     birthday
    0.79
    Activations Density 0.217%

    No Known Activations