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. 23906
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific commands or actions in a computer programming context

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to donations and financial contributions

    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
    ord
    -0.84
    ucks
    -0.82
    avier
    -0.81
    adem
    -0.75
    lahoma
    -0.74
    opol
    -0.72
    roman
    -0.72
    ffen
    -0.68
    orn
    -0.67
    atron
    -0.67
    POSITIVE LOGITS
    NING
    1.40
    ING
    1.33
    MAN
    1.33
    ABLE
    1.32
    NESS
    1.31
    MENT
    1.31
    INGS
    1.31
    BOOK
    1.31
    ANCE
    1.29
    INESS
    1.28
    Activations Density 0.140%

    No Known Activations