© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6168
    Prev
    Next
    INDEX
    Explanations

    causes or reasons for actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "prompted" in various contexts

    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
     Atomic
    -0.67
    lim
    -0.63
    aths
    -0.61
     rot
    -0.57
     Think
    -0.57
     everyday
    -0.57
    th
    -0.57
    ths
    -0.56
    know
    -0.56
     ut
    -0.55
    POSITIVE LOGITS
     prompted
    3.49
     spurred
    2.10
     provoked
    2.07
     sparked
    2.04
     prompts
    1.95
     triggered
    1.77
     prompting
    1.59
     alerted
    1.49
     spawned
    1.48
     greeted
    1.43
    Activations Density 0.016%

    No Known Activations