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. 6027
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or influencing a situation

    oai_token-act-pair · gpt-3.5-turbo

    actions related to promoting, establishing, or enhancing various efforts or initiatives

    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
    Downloadha
    -0.76
    arij
    -0.73
    option
    -0.67
    Fax
    -0.66
    -----------
    -0.65
    pmwiki
    -0.64
    NetMessage
    -0.63
    never
    -0.62
    sbm
    -0.62
     Ago
    -0.62
    POSITIVE LOGITS
    uate
    0.77
    veland
    0.73
     amplify
    0.67
    burse
    0.67
    escape
    0.65
     paternity
    0.62
     digestion
    0.62
    etch
    0.62
     snowball
    0.60
     budding
    0.59
    Activations Density 0.133%

    No Known Activations