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. 521
    Prev
    Next
    INDEX
    Explanations

    URLs within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "here" indicating locations or sources of additional information

    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
    omore
    -0.74
    visors
    -0.69
    itialized
    -0.67
    upuncture
    -0.65
    iven
    -0.65
    ammy
    -0.64
    ometry
    -0.60
    amac
    -0.59
    tone
    -0.58
    mong
    -0.57
    POSITIVE LOGITS
    tical
    1.22
    tics
    1.17
    abouts
    1.10
    tic
    1.05
    here
    0.85
    ridges
    0.75
     âĢº
    0.73
     âĨij
    0.73
     guiActiveUn
    0.72
    with
    0.69
    Activations Density 0.046%

    No Known Activations