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. 3704
    Prev
    Next
    INDEX
    Explanations

    names or places containing the letters "res"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or venues

    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
     Qing
    -0.60
     caucuses
    -0.60
    VERTISEMENT
    -0.60
    glers
    -0.60
    \\\\\\\\\\\\\\\\
    -0.60
    doms
    -0.58
     strings
    -0.57
     "{
    -0.57
     Wilhelm
    -0.56
     pound
    -0.56
    POSITIVE LOGITS
    istance
    1.29
    idency
    1.24
    cue
    1.22
    olutions
    1.08
    erve
    1.06
    pring
    1.06
    idence
    1.05
    urrection
    1.03
    idents
    1.02
    cale
    1.01
    Activations Density 0.016%

    No Known Activations