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. 3-RES-JB
    6. 942
    Prev
    Next
    INDEX
    Explanations

    words related to amphetamines and amplifiers

    oai_token-act-pair · gpt-3.5-turbo

    references to amphetamines and related substances

    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
    SHIP
    -0.90
    naire
    -0.72
    tale
    -0.68
     Citizens
    -0.66
    BLIC
    -0.66
    fare
    -0.65
     Draper
    -0.65
    ROR
    -0.65
     Cannes
    -0.64
    theless
    -0.64
    POSITIVE LOGITS
    hetamine
    1.54
    ulla
    1.05
     amp
    1.04
    het
    0.98
    ules
    0.89
    urations
    0.86
    ule
    0.86
    ilit
    0.84
     amps
    0.83
    iah
    0.82
    Activations Density 0.005%

    No Known Activations