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. 2-RES-JB
    6. 2737
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific location or event

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Val" or related variations, likely indicating a focus on the concept or theme associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pread
    -0.74
    ãģ¦
    -0.71
    hearted
    -0.65
    lihood
    -0.65
    nown
    -0.65
    peed
    -0.64
    ften
    -0.64
    ngth
    -0.63
    ItemTracker
    -0.61
     WTC
    -0.61
    POSITIVE LOGITS
    idation
    1.20
    idated
    0.98
    idate
    0.97
    ibr
    0.93
    uation
    0.91
    ulner
    0.91
    ueless
    0.90
    idates
    0.89
     Val
    0.86
    Val
    0.85
    Activations Density 0.007%

    No Known Activations