© 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. 9-RES-JB
    6. 3625
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or transitions between different locations or contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a direction or a destination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ended
    -0.78
     differed
    -0.77
    puff
    -0.74
    ^^
    -0.73
    Written
    -0.73
    don
    -0.72
    /)
    -0.72
    rs
    -0.71
    /*
    -0.71
    irez
    -0.70
    POSITIVE LOGITS
     outright
    0.81
     downright
    0.78
    ilet
    0.77
     rooft
    0.77
    pless
    0.74
    asters
    0.72
     nonexistent
    0.71
     overflowing
    0.70
     infinity
    0.70
    asted
    0.69
    Activations Density 0.087%

    No Known Activations