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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8742
    Prev
    Next
    INDEX
    Explanations

    phrases surrounded by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pit
    -0.69
     skelet
    -0.67
    rieved
    -0.66
    iors
    -0.64
    kw
    -0.64
     slam
    -0.62
     tremend
    -0.62
    uct
    -0.61
     prenatal
    -0.61
    ient
    -0.61
    POSITIVE LOGITS
    amazon
    0.74
    ablishment
    0.74
    Administ
    0.72
     Whilst
    0.71
     ie
    0.69
    Firstly
    0.68
     Alternatively
    0.67
    jriwal
    0.66
    ++++++++++++++++
    0.65
    pler
    0.65
    Activations Density 0.040%

    No Known Activations