Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1270
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement in water

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions and processes involving manipulation or interaction

    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
    nih
    -0.81
    INAL
    -0.80
    querque
    -0.80
    ccording
    -0.78
    Īè
    -0.75
    ij士
    -0.74
    ¥
    -0.73
     McCull
    -0.72
    ģĸ
    -0.72
    £ı
    -0.71
    POSITIVE LOGITS
    nesday
    1.07
    lich
    0.80
    fleet
    0.76
    cum
    0.74
    meter
    0.72
    maker
    0.67
    ipeg
    0.65
    glers
    0.64
    risome
    0.64
     Wax
    0.64
    Activations Density 0.051%

    No Known Activations