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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 6817
    Prev
    Next
    INDEX
    Explanations

    authors of books or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their works

    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
    ooth
    -0.67
     specificity
    -0.63
    limits
    -0.62
    asia
    -0.60
    ensen
    -0.59
     uncond
    -0.59
    zik
    -0.59
    pter
    -0.58
     turb
    -0.58
    tone
    -0.58
    POSITIVE LOGITS
    thood
    0.77
    olkien
    0.74
     memoir
    0.70
    ternity
    0.69
     [|
    0.69
    @#&
    0.68
     Awakens
    0.68
     Bearing
    0.68
    ĻĤ
    0.68
    stellar
    0.68
    Activations Density 0.072%

    No Known Activations