© 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. 9-RES-JB
    11. 14261
    Prev
    Next
    INDEX
    Explanations

    mentions of varying levels of intensity or quantity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify levels or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sy
    -0.66
    issance
    -0.66
    stown
    -0.59
    eur
    -0.58
    aign
    -0.58
    BILITY
    -0.58
    reci
    -0.57
    ties
    -0.57
    ulus
    -0.56
    Delivery
    -0.53
    POSITIVE LOGITS
     thereof
    1.27
    pace
    1.20
    paces
    1.19
     of
    1.13
    poons
    1.12
    etting
    1.01
    pring
    0.97
    cale
    0.96
    hift
    0.96
    ourcing
    0.90
    Activations Density 0.425%

    No Known Activations