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. 6464
    Prev
    Next
    INDEX
    Explanations

    keywords related to storms or storm-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "Storm" or related characters/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
    entary
    -0.95
    ĸļ
    -0.90
    ADRA
    -0.85
    terior
    -0.84
    ablished
    -0.81
    ASED
    -0.80
    untu
    -0.80
    ately
    -0.79
    ablishment
    -0.78
    duction
    -0.78
    POSITIVE LOGITS
    tro
    1.32
     troopers
    0.99
     Trooper
    0.97
    bringer
    0.96
     Storm
    0.91
    claw
    0.89
     trooper
    0.85
    water
    0.84
    light
    0.83
    front
    0.82
    Activations Density 0.012%

    No Known Activations