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. 1-RES-JB
    6. 19429
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used as text decorations

    oai_token-act-pair · gpt-3.5-turbo

    the character or symbol 'â̦'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depletion
    -0.74
     scatter
    -0.72
     cradle
    -0.72
     submerged
    -0.70
     dispar
    -0.70
     bipolar
    -0.70
     antip
    -0.69
     richer
    -0.68
     snail
    -0.68
     grieving
    -0.68
    POSITIVE LOGITS
    â̦â̦â̦â̦
    0.94
    etc
    0.93
    yet
    0.92
    WHERE
    0.90
    =#
    0.85
    >[
    0.84
    â̦â̦â̦â̦â̦â̦â̦â̦
    0.82
    NAT
    0.82
    AUD
    0.81
    ..
    0.80
    Activations Density 0.022%

    No Known Activations