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. 0-RES-JB
    6. 21459
    Prev
    Next
    INDEX
    Explanations

    terms related to current status or condition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the current state or condition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spam
    -0.85
     mom
    -0.83
     mafia
    -0.81
     scary
    -0.81
     fake
    -0.81
     Timeline
    -0.77
     priorit
    -0.77
     mini
    -0.76
     themed
    -0.76
     timeline
    -0.76
    POSITIVE LOGITS
    ,—
    1.79
     presently
    1.46
     thereto
    1.41
     doubtless
    1.39
    soever
    1.37
     hitherto
    1.35
     thence
    1.34
     chiefly
    1.32
     therein
    1.31
     scarcely
    1.30
    Activations Density 0.183%

    No Known Activations