Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 21417
    Prev
    Next
    INDEX
    Explanations

    top rankings or lists

    oai_token-act-pair · gpt-3.5-turbo

    references to ranking or listing items, particularly in a "Top" format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.75
     Gaul
    -0.71
    Äĩ
    -0.69
    riages
    -0.64
     hunger
    -0.64
    BILITY
    -0.63
     ascert
    -0.63
    vous
    -0.63
     detachment
    -0.63
    ngth
    -0.63
    POSITIVE LOGITS
    eka
    1.08
    Top
    0.97
    most
    0.96
    ographical
    0.91
     Top
    0.88
    top
    0.86
    ography
    0.84
    TOP
    0.84
    Tier
    0.84
    Boss
    0.81
    Activations Density 0.022%

    No Known Activations