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. 4975
    Prev
    Next
    INDEX
    Explanations

    phrases relating to sports drafts or selections

    oai_token-act-pair · gpt-3.5-turbo

    references to draft picks in sports

    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
     interf
    -0.80
    english
    -0.77
    isf
    -0.70
     lapt
    -0.70
    STD
    -0.68
    Sea
    -0.67
    igi
    -0.67
     hem
    -0.66
    ilit
    -0.66
    loo
    -0.66
    POSITIVE LOGITS
    士
    0.88
     Picks
    0.86
     picks
    0.84
    pocket
    0.83
    axe
    0.83
     pick
    0.81
     (#
    0.78
    Pick
    0.77
    opoulos
    0.76
    onom
    0.73
    Activations Density 0.025%

    No Known Activations