© 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. 6-RES-JB
    11. 2637
    Prev
    Next
    INDEX
    Explanations

    phrases related to shooting or aiming

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "shoot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    States
    -0.81
    verse
    -0.76
    undai
    -0.76
    ebook
    -0.74
    $$$$
    -0.73
    roe
    -0.72
    emonic
    -0.71
    Eng
    -0.70
    STEP
    -0.69
    anse
    -0.65
    POSITIVE LOGITS
     shoot
    0.90
     hoops
    0.85
    outs
    0.84
     weddings
    0.81
    nikov
    0.78
     Shoot
    0.77
     shooting
    0.77
     shoots
    0.72
    around
    0.71
    linger
    0.70
    Activations Density 0.031%

    No Known Activations