© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16066
    Prev
    Next
    INDEX
    Explanations

    numerical values or technical information

    oai_token-act-pair · gpt-3.5-turbo

    various types of punctuation and bracketed expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itory
    -0.75
     administrator
    -0.74
    ching
    -0.72
    enta
    -0.68
    ©¶æ
    -0.67
     hall
    -0.67
    acle
    -0.66
    iter
    -0.66
     pitch
    -0.66
    ating
    -0.65
    POSITIVE LOGITS
    )].
    0.95
    >]
    0.88
    ONSORED
    0.82
    ]),
    0.81
    )]
    0.81
    )))
    0.78
    ]).
    0.77
    ],[
    0.77
     Frames
    0.74
    )[
    0.73
    Activations Density 0.016%

    No Known Activations