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. 13006
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological advancements and breakthroughs, especially in the context of different industries, such as music or electronics

    oai_token-act-pair · gpt-3.5-turbo

    key aspects of significant events or achievements related to popular culture

    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
     memos
    -0.69
    artment
    -0.66
     Contract
    -0.64
     Transcript
    -0.62
     incorrectly
    -0.60
     briefed
    -0.60
     constitution
    -0.60
     Lack
    -0.60
     Conditions
    -0.59
     told
    -0.59
    POSITIVE LOGITS
     leaps
    0.96
     acclaim
    0.85
     impressive
    0.85
     debut
    0.84
     blockbuster
    0.84
     renown
    0.82
    elight
    0.81
    uably
    0.80
     acclaimed
    0.80
    ĸļ
    0.80
    Activations Density 1.061%

    No Known Activations