© 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. 2-RES-JB
    11. 12962
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names and terms related to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ships
    -0.74
     Destination
    -0.72
     Observer
    -0.71
    osate
    -0.69
    ship
    -0.69
    sburgh
    -0.68
     Floyd
    -0.65
     Stephenson
    -0.65
     Bulgarian
    -0.62
    ...]
    -0.61
    POSITIVE LOGITS
     Das
    0.94
    irez
    0.89
    abase
    0.77
    ãĥ¯ãĥ³
    0.77
    Filename
    0.77
    pex
    0.76
    ãĤ´ãĥ³
    0.76
    plet
    0.75
    gee
    0.74
    Cod
    0.74
    Activations Density 0.005%

    No Known Activations