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. 13655
    Prev
    Next
    INDEX
    Explanations

    technical details or specific features about products or machines

    oai_token-act-pair · gpt-3.5-turbo

    key features and characteristics of subjects or items discussed in the text

    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
    arat
    -0.68
    events
    -0.64
     furthermore
    -0.64
     violates
    -0.63
    ounces
    -0.63
    Registered
    -0.60
    âĿ
    -0.60
    hops
    -0.60
    ishers
    -0.60
    reads
    -0.59
    POSITIVE LOGITS
     consistency
    0.73
    maxwell
    0.69
     applic
    0.68
    arcity
    0.64
     Chap
    0.60
     Qualcomm
    0.60
     basil
    0.58
     proximity
    0.58
     versatility
    0.57
     inconsistency
    0.57
    Activations Density 0.295%

    No Known Activations