© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 14720
    Prev
    Next
    INDEX
    Explanations

    phrases related to comments or annotations

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Rem" in various contexts

    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
    gerald
    -0.80
    glers
    -0.77
    tips
    -0.73
    SHIP
    -0.70
     McCabe
    -0.63
     Labrador
    -0.62
    OPLE
    -0.61
     sack
    -0.60
    tie
    -0.60
    FP
    -0.60
    POSITIVE LOGITS
    nants
    1.19
    edy
    1.13
    arkable
    1.10
    ovable
    1.08
    oving
    1.07
    ainer
    1.03
    inder
    1.00
    ainers
    0.99
    arks
    0.98
    ont
    0.94
    Activations Density 0.004%

    No Known Activations