© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    mentions of pharmaceutical terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "arm" or related terms

    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
     Zub
    -0.70
     ever
    -0.65
     visibility
    -0.65
     Pref
    -0.64
     futures
    -0.64
     polyg
    -0.64
     consum
    -0.63
     GET
    -0.62
     buckets
    -0.61
     intrinsic
    -0.61
    POSITIVE LOGITS
    arm
    4.50
    arms
    2.88
    ARM
    2.34
    armed
    2.19
    arming
    2.05
    Arm
    1.80
    arma
    1.78
     arm
    1.46
     Arm
    1.35
     arms
    1.34
    Activations Density 0.005%

    No Known Activations