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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 15124
    Prev
    Next
    INDEX
    Explanations

    names starting with "Jo"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jo" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     difference
    -0.65
    rified
    -0.62
     Greeks
    -0.62
     vectors
    -0.62
    binary
    -0.61
     Iranians
    -0.61
    flies
    -0.61
     Europeans
    -0.60
     Horizons
    -0.60
     bombard
    -0.59
    POSITIVE LOGITS
    jo
    1.53
    aquin
    1.16
    zzo
    1.05
    JO
    1.00
    Jo
    0.98
    vernment
    0.98
    atana
    0.96
    ffee
    0.95
    ichi
    0.94
    itsu
    0.89
    Activations Density 0.007%

    No Known Activations