© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns or pronouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize perspective and opinions

    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
    apons
    -0.87
    ////////////////
    -0.78
    Guard
    -0.74
    sbm
    -0.71
    fml
    -0.70
    apon
    -0.70
    LAN
    -0.66
    esm
    -0.65
    è¦ļéĨĴ
    -0.64
    maid
    -0.64
    POSITIVE LOGITS
     Nieto
    0.72
     exaggeration
    0.70
     causation
    0.68
     differentiation
    0.68
     Genocide
    0.68
     reversal
    0.64
     victory
    0.64
    ozy
    0.64
     approximate
    0.63
     attack
    0.62
    Activations Density 0.204%

    No Known Activations