© 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. 17053
    Prev
    Next
    INDEX
    Explanations

    years and term-related to college or education

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and events in a chronological context

    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
     ...
    -1.61
     ..."
    -1.52
     ....
    -1.46
     âĢİ
    -1.42
     ''
    -1.34
     ......
    -1.27
     -
    -1.21
    ...
    -1.10
    "...
    -1.10
     �
    -1.06
    POSITIVE LOGITS
    –
    2.36
    .–
    2.02
    ––
    1.45
    âĪĴ
    1.25
    —-
    1.20
    ÃĹ
    1.12
     âĪ¼
    1.11
    âĢIJ
    1.05
    âĢķ
    0.95
    >[
    0.94
    Activations Density 0.152%

    No Known Activations