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. 22795
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences or emotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that explore the concept of experience

    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
    oak
    -0.67
    dash
    -0.65
    NetMessage
    -0.62
     Inher
    -0.62
    eous
    -0.61
    riad
    -0.61
    Continue
    -0.61
    Kings
    -0.61
    camp
    -0.60
     Galile
    -0.59
    POSITIVE LOGITS
     entails
    1.15
     means
    1.12
     meant
    1.04
     takes
    0.99
     entail
    0.98
     Means
    0.98
     mean
    0.97
     feels
    0.96
     boils
    0.88
     signifies
    0.86
    Activations Density 0.043%

    No Known Activations