© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6580
    Prev
    Next
    INDEX
    Explanations

    fragments of casual conversation containing phrases like "I think," "And I think," and "you hear that."

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal opinions or beliefs expressed in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    ¨
    -0.78
    ãĥ¯ãĥ³
    -0.77
    COMPLE
    -0.77
    eaturing
    -0.76
    ¶ħ
    -0.71
     comprised
    -0.71
    cele
    -0.71
    Þ
    -0.71
     victorious
    -0.70
    POSITIVE LOGITS
     maybe
    0.90
    Alternatively
    0.89
    maybe
    0.87
     anecdotal
    0.83
     argues
    0.82
    Maybe
    0.82
     Suppose
    0.82
     Maybe
    0.81
     bothers
    0.79
    Others
    0.79
    Activations Density 0.793%

    No Known Activations