© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    numerical values representing a 'two' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the number "two" in various contexts

    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
    yles
    -0.76
     Shutterstock
    -0.67
     Janeiro
    -0.61
     Uruguay
    -0.61
    raits
    -0.60
     Thomson
    -0.59
    76561
    -0.57
     embassies
    -0.57
    itives
    -0.56
     Devices
    -0.56
    POSITIVE LOGITS
    fold
    1.05
    quel
    1.02
     dimensional
    0.94
    peat
    0.94
    -
    0.89
    dimensional
    0.88
    âĢij
    0.85
    teenth
    0.85
    license
    0.82
    ministic
    0.79
    Activations Density 0.076%

    No Known Activations