© 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. 1-RES-JB
    6. 879
    Prev
    Next
    INDEX
    Explanations

    phrases related to directions or pathways

    oai_token-act-pair · gpt-3.5-turbo

    references to a "path."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Staples
    -0.63
    odium
    -0.61
    ettings
    -0.60
     occasions
    -0.59
    efficients
    -0.59
    rencies
    -0.59
    initions
    -0.57
    itu
    -0.56
    orpor
    -0.55
     Franks
    -0.54
    POSITIVE LOGITS
     paths
    1.13
     path
    1.09
    path
    0.94
    finder
    0.93
    finding
    0.90
     pathway
    0.86
    ozo
    0.83
     PATH
    0.81
    owitz
    0.78
    ways
    0.78
    Activations Density 0.012%

    No Known Activations