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. 10-RES-JB
    6. 13219
    Prev
    Next
    INDEX
    Explanations

    determining factors or decisions being discussed

    oai_token-act-pair · gpt-3.5-turbo

    complex statements about decision-making and the collective actions of a group

    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
     unsurprisingly
    -0.81
     .)
    -0.72
     "...
    -0.71
     Alas
    -0.68
    surprisingly
    -0.65
     Whilst
    -0.65
     Torrent
    -0.60
     favoured
    -0.60
     recognised
    -0.60
     Beware
    -0.60
    POSITIVE LOGITS
    âĢ
    1.53
    »
    1.39
    âĢij
    1.39
    âĢķ
    1.33
    ***
    1.28
    –
    1.24
    —-
    1.24
    âĺ
    1.23
    ****
    1.21
    *****
    1.20
    Activations Density 0.801%

    No Known Activations