© 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. 2-RES-JB
    11. 17771
    Prev
    Next
    INDEX
    Explanations

    chemical compounds or elements, specifically focusing on hydroxyl groups

    oai_token-act-pair · gpt-3.5-turbo

    references to hydroxyl (OH) groups and related chemical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķ
    -0.76
    ãĥķãĤ©
    -0.75
     totality
    -0.73
    guard
    -0.72
    unct
    -0.72
    ãĥ¯
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.71
     PTS
    -0.67
    ãĤ°
    -0.65
    eers
    -0.63
    POSITIVE LOGITS
    OH
    1.29
    OF
    0.99
    OM
    0.95
    OME
    0.95
    OOD
    0.93
    azard
    0.90
    ospital
    0.90
    ISTORY
    0.89
    FU
    0.88
    ONT
    0.87
    Activations Density 0.008%

    No Known Activations