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

    Neuronpedia

    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. 0-RES-JB
    11. 19125
    Prev
    Next
    INDEX
    Explanations

    items or objects that are replaced or replicated

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with replicas and replacements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heights
    -0.75
    ONT
    -0.73
    gie
    -0.73
    ENCY
    -0.70
    aghan
    -0.70
    alty
    -0.68
    mph
    -0.68
    azar
    -0.65
     Acid
    -0.65
     Agreement
    -0.64
    POSITIVE LOGITS
     repl
    4.06
     Repl
    2.20
    repl
    2.20
    Repl
    1.99
     reprodu
    1.97
     replica
    1.88
     replay
    1.86
     replication
    1.84
     replicate
    1.75
     replicated
    1.69
    Activations Density 0.014%

    No Known Activations