Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 22732
    Prev
    Next
    INDEX
    Explanations

    mentions of the AK-47 assault rifle

    oai_token-act-pair · gpt-3.5-turbo

    references to the AK-47 rifle and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wall
    -0.76
    omorphic
    -0.76
    metry
    -0.74
    spection
    -0.72
    uses
    -0.72
    clude
    -0.71
    gaard
    -0.71
    voy
    -0.70
    perties
    -0.70
    urally
    -0.70
    POSITIVE LOGITS
    AY
    1.28
    KA
    1.14
    IN
    1.14
    AX
    1.13
    INO
    1.10
    LA
    1.08
    MU
    1.08
    A
    1.07
    IK
    1.07
    KI
    1.06
    Activations Density 0.040%

    No Known Activations