© 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. 10-RES-JB
    11. 14058
    Prev
    Next
    INDEX
    Explanations

    terms related to philosophical concepts or academic topics

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kosher
    -0.65
    FUL
    -0.64
     Airl
    -0.63
     Famous
    -0.62
     bartender
    -0.60
     Forgotten
    -0.60
     Sapphire
    -0.60
     uphill
    -0.60
    Rated
    -0.59
     unused
    -0.59
    POSITIVE LOGITS
    ism
    1.32
    itism
    1.27
    ivism
    1.25
    rification
    1.23
    icism
    1.16
    utics
    1.14
    ogenesis
    1.13
    osis
    1.13
    atism
    1.12
    ativity
    1.11
    Activations Density 0.412%

    No Known Activations