© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 6361
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ser"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of Serbian entities or names

    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
    ORN
    -0.81
    Rated
    -0.80
    INGTON
    -0.78
    enegger
    -0.76
    AUT
    -0.76
    ESCO
    -0.76
    OWS
    -0.73
    STEP
    -0.70
    ATS
    -0.69
    erella
    -0.69
    POSITIVE LOGITS
    geant
    0.93
    onial
    0.90
    archs
    0.90
    rha
    0.88
    iffs
    0.88
    ials
    0.87
    rano
    0.87
    otonin
    0.85
    mons
    0.81
    uitous
    0.79
    Activations Density 0.007%

    No Known Activations