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. 1058
    Prev
    Next
    INDEX
    Explanations

    phrases related to justice, morality, and identity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of duality or conflicting identities

    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
     theirs
    -0.48
    Availability
    -0.48
    ).[
    -0.47
    .).
    -0.47
     nevertheless
    -0.45
     nonetheless
    -0.44
    +.
    -0.44
     Ves
    -0.43
     eventual
    -0.42
    aults
    -0.42
    POSITIVE LOGITS
    ':
    0.63
    ?'
    0.62
    \":
    0.56
    \",
    0.50
    !'
    0.49
     ',
    0.47
    %"
    0.47
     Replay
    0.47
     ['
    0.46
    '?
    0.46
    Activations Density 3.310%

    No Known Activations