© 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. 0-RES-JB
    6. 11895
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks or symbols like "]"

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥİ
    -0.66
     blight
    -0.59
     ));
    -0.54
     infl
    -0.53
     tur
    -0.52
     lim
    -0.51
     sa
    -0.51
     free
    -0.51
     dep
    -0.49
     beaches
    -0.49
    POSITIVE LOGITS
    .]
    3.72
    !]
    2.97
    ?]
    2.96
    :]
    2.76
    "]
    2.73
    ...]
    2.67
    â̦]
    2.65
    ]."
    2.55
    ].
    2.46
    ]]
    2.46
    Activations Density 0.009%

    No Known Activations