© 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. 6-RES-JB
    6. 3529
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'Opp' with a rating of 8 or higher

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Opp" and its variations, indicating a focus on opposition or opposing viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.85
    çīĪ
    -0.69
    è¯
    -0.69
    GO
    -0.69
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    WAYS
    -0.64
    ä¹ĭ
    -0.64
     Fork
    -0.63
     fingertips
    -0.63
    Series
    -0.61
    POSITIVE LOGITS
    onent
    1.68
    osite
    1.56
    ortun
    1.53
    onents
    1.51
    osition
    1.46
    osing
    1.25
    osed
    1.18
    ressive
    1.18
    ression
    1.16
    ressor
    1.13
    Activations Density 0.014%

    No Known Activations