© 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. 1-RES-JB
    11. 20756
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Walk" in various contexts

    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
     competing
    -0.74
    arial
    -0.72
    cffff
    -0.71
     serotonin
    -0.70
     ammon
    -0.67
    rss
    -0.65
    milo
    -0.65
     cir
    -0.64
    ãĥª
    -0.64
    egal
    -0.64
    POSITIVE LOGITS
    Walk
    1.30
     Walk
    1.20
    walk
    1.19
    walker
    0.98
    abouts
    0.95
    walking
    0.86
    about
    0.86
    ways
    0.86
    breaker
    0.81
     Breaker
    0.80
    Activations Density 0.005%

    No Known Activations