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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 8017
    Prev
    Next
    INDEX
    Explanations

    contexts related to dispensing items or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dispensing in a medical or regulatory context

    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
     Skydragon
    -0.69
     Codec
    -0.69
    RAFT
    -0.68
    emouth
    -0.65
    alkyrie
    -0.65
    onda
    -0.65
    hiro
    -0.64
    ilde
    -0.64
     BaseType
    -0.63
    ynthesis
    -0.63
    POSITIVE LOGITS
     dispens
    1.18
    ership
    1.03
    ery
    0.97
    ation
    0.88
    er
    0.85
    erers
    0.81
    itory
    0.77
    cess
    0.76
    ating
    0.76
    ers
    0.74
    Activations Density 0.022%

    No Known Activations