© 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. 11-RES-JB
    11. 4763
    Prev
    Next
    INDEX
    Explanations

    information related to what someone needs to know or do.

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential information or knowledge that someone should be aware of

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reconstruction
    -0.68
     Miko
    -0.60
     appell
    -0.57
     Estate
    -0.57
     yielding
    -0.55
     rehabilitation
    -0.54
     expulsion
    -0.54
    Output
    -0.54
     Plat
    -0.54
     honored
    -0.54
    POSITIVE LOGITS
    know
    1.36
     know
    1.31
     KNOW
    1.30
     Know
    1.26
    Know
    1.22
     knows
    1.02
     knew
    0.93
     knowing
    0.83
     Knowing
    0.75
     knowledge
    0.72
    Activations Density 0.102%

    No Known Activations