© 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. 24513
    Prev
    Next
    INDEX
    Explanations

    code snippets related to caching and implementation details

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and phrases related to software development and implementation

    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
     Alph
    -0.72
    uncle
    -0.70
     Kingston
    -0.69
    intosh
    -0.68
    unts
    -0.68
    enne
    -0.68
     outwe
    -0.67
     Cyr
    -0.66
    atro
    -0.66
    mega
    -0.66
    POSITIVE LOGITS
    Callback
    1.26
    Events
    1.20
     callback
    1.19
     Events
    1.17
    Listener
    1.16
    Dispatch
    1.14
    Event
    1.13
     notify
    1.10
    Trigger
    1.07
     Observ
    1.06
    Activations Density 0.241%

    No Known Activations