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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18189
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and their initiatives

    oai_token-act-pair · gpt-3.5-turbo

    corporate initiatives and support for technology development

    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
     UNCLASSIFIED
    -0.79
     ILCS
    -0.71
    Reviewer
    -0.69
    anon
    -0.69
    },
    -0.68
    ''.
    -0.66
    trump
    -0.65
    gat
    -0.65
    peace
    -0.64
    ande
    -0.64
    POSITIVE LOGITS
     customers
    0.91
     pricing
    0.88
     licensing
    0.88
     its
    0.83
     SDK
    0.83
     partnerships
    0.83
     DRM
    0.81
     customer
    0.80
     Chromebook
    0.80
     patents
    0.78
    Activations Density 0.901%

    No Known Activations