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. 3842
    Prev
    Next
    INDEX
    Explanations

    items related to crime, including weapons and theft

    oai_token-act-pair · gpt-3.5-turbo

    references to specific incidents involving guns or weapons

    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
     stages
    -0.89
     stadiums
    -0.86
     diets
    -0.82
     entrants
    -0.81
     arenas
    -0.81
     communities
    -0.80
     audiences
    -0.77
     Expect
    -0.76
     valleys
    -0.76
     empires
    -0.76
    POSITIVE LOGITS
     drawer
    1.27
     confiscated
    1.23
     holster
    1.20
     necklace
    1.15
     clasp
    1.13
     bracelet
    1.11
     lodged
    1.10
     engraved
    1.09
     pouch
    1.09
     malfunction
    1.05
    Activations Density 0.531%

    No Known Activations