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. 23779
    Prev
    Next
    INDEX
    Explanations

    names that appear to be of personal interest or importance

    oai_token-act-pair · gpt-3.5-turbo

    the presence of names or terms associated with individuals or entities (likely related to sports or entertainment)

    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
     faint
    -0.61
     sarc
    -0.60
     srfAttach
    -0.59
     rusty
    -0.59
    ãĤª
    -0.59
     constit
    -0.59
    atoes
    -0.58
     foreseeable
    -0.57
    ourning
    -0.57
     calories
    -0.56
    POSITIVE LOGITS
    neys
    0.96
    dan
    0.86
    ernaut
    0.82
    eki
    0.78
     Marriott
    0.77
    EStream
    0.76
    ansen
    0.75
     Mehran
    0.72
    TAG
    0.72
     Whedon
    0.71
    Activations Density 0.079%

    No Known Activations