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. 24271
    Prev
    Next
    INDEX
    Explanations

    terms related to communication or communal activities/themes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commun" and its variations, indicating a focus on themes associated with communication and community

    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
    BALL
    -0.90
    olkien
    -0.85
    OPLE
    -0.75
    IELD
    -0.71
    OHN
    -0.69
     Lank
    -0.69
    DonaldTrump
    -0.68
    terday
    -0.66
    !/
    -0.65
    leaf
    -0.64
    POSITIVE LOGITS
    icator
    1.47
    icators
    1.32
    icable
    1.31
    icating
    1.30
    icative
    1.20
    icate
    1.13
    icated
    1.12
    ications
    1.11
    ique
    1.10
    icates
    1.10
    Activations Density 0.017%

    No Known Activations