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. 10-RES-JB
    6. 4075
    Prev
    Next
    INDEX
    Explanations

    specific mentions or actions related to individuals or their identities

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and variations of existence or state being in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olutions
    -0.89
     increments
    -0.82
    artments
    -0.81
     Strategies
    -0.81
     resolutions
    -0.77
    urry
    -0.75
    osit
    -0.72
    results
    -0.70
    heny
    -0.70
     strategies
    -0.68
    POSITIVE LOGITS
     worshipped
    1.18
     assassinated
    1.13
     alive
    1.13
     deceased
    1.11
     remembered
    1.10
     immortal
    1.09
     revered
    1.07
     dead
    1.07
     portrayed
    1.06
     depicted
    1.02
    Activations Density 0.381%

    No Known Activations