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. 4348
    Prev
    Next
    INDEX
    Explanations

    technical information such as article sections or meta information within documents

    oai_token-act-pair · gpt-3.5-turbo

    text that is empty or lacks meaningful content

    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
     reper
    -0.69
     eleph
    -0.65
    ledged
    -0.61
     tradem
    -0.61
     amnesty
    -0.60
    ilty
    -0.60
     interven
    -0.60
     estranged
    -0.59
     initi
    -0.58
     embargo
    -0.58
    POSITIVE LOGITS
    Untitled
    1.09
    Abstract
    1.07
    WASHINGTON
    1.06
    CLOSE
    1.05
    Description
    1.04
    Overview
    1.00
    Still
    0.99
    Trivia
    0.98
    CTV
    0.97
    Breaking
    0.96
    Activations Density 0.131%

    No Known Activations