© 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. 21379
    Prev
    Next
    INDEX
    Explanations

    instances of words related to research and scholarly activities

    oai_token-act-pair · gpt-3.5-turbo

    abstract concepts related to differences and classifications

    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
     Skydragon
    -0.52
     attRot
    -0.51
    Instead
    -0.46
     });
    -0.46
     sqor
    -0.46
    %.
    -0.45
    $.
    -0.45
    +.
    -0.44
    ãĢĤ
    -0.44
     };
    -0.43
    POSITIVE LOGITS
     in
    1.05
     aboard
    0.88
     amongst
    0.88
     inside
    0.87
     within
    0.86
     among
    0.84
     on
    0.79
     throughout
    0.78
     anywhere
    0.78
    among
    0.76
    Activations Density 1.579%

    No Known Activations