Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16571
    Prev
    Next
    INDEX
    Explanations

    topics related to current events, such as the Fukushima situation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -1.05
    ilitation
    -0.73
    bley
    -0.70
    uly
    -0.68
    icter
    -0.66
     embr
    -0.66
    chid
    -0.65
     favoured
    -0.65
     DOT
    -0.63
    swer
    -0.63
    POSITIVE LOGITS
    Enlarge
    0.94
    Legendary
    0.88
    Actor
    0.83
    Associated
    0.70
    Adapt
    0.69
    ROM
    0.68
    Contribut
    0.67
    Episode
    0.67
    Neal
    0.66
    çĶŁ
    0.66
    Activations Density 0.139%

    No Known Activations