Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20537
    Prev
    Next
    INDEX
    Explanations

    pronouns ('your', 'my', 'our', 'their') followed by possessive references, and words related to self-reflection and empowerment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal and collective ownership or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ket
    -0.80
    haus
    -0.79
    ucc
    -0.76
    075
    -0.75
    ij士
    -0.71
    warn
    -0.68
    asus
    -0.67
    edd
    -0.67
    021
    -0.67
    8000
    -0.67
    POSITIVE LOGITS
     individuality
    1.48
     passions
    1.36
     own
    1.36
     emotions
    1.32
     deepest
    1.31
    selves
    1.28
     selves
    1.28
     sexuality
    1.27
     desires
    1.25
     surroundings
    1.22
    Activations Density 0.212%

    No Known Activations