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. 23801
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or individuals, specifically focusing on names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to characters, creatures, or entities associated with the "Hawk" and "Scorpion" themes

    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
     conduc
    -0.82
     corrid
    -0.82
    aps
    -0.81
     unden
    -0.78
    perature
    -0.77
    mediately
    -0.77
     cryst
    -0.76
     pse
    -0.76
    ¿
    -0.75
    uers
    -0.74
    POSITIVE LOGITS
    hawk
    1.16
     Nebula
    1.01
    hunter
    1.01
     Owl
    0.98
     Riders
    0.98
    fish
    0.96
     Isle
    0.95
     Rider
    0.95
     Claw
    0.94
     Graveyard
    0.92
    Activations Density 0.115%

    No Known Activations