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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 511
    Prev
    Next
    INDEX
    Explanations

    referencing drugs, particularly methamphetamine

    oai_token-act-pair · gpt-3.5-turbo

    references to meth and related substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accessory
    -0.80
    Reviewer
    -0.78
     Dull
    -0.74
    DragonMagazine
    -0.72
     Blind
    -0.71
     Overs
    -0.70
     Gladiator
    -0.70
    hips
    -0.70
    GGGGGGGG
    -0.70
     Arms
    -0.70
    POSITIVE LOGITS
    amphetamine
    1.11
    ilit
    1.08
    oxy
    0.97
     meth
    0.97
    oglobin
    0.89
    inks
    0.88
    otic
    0.84
    anyahu
    0.81
    ict
    0.81
    hetamine
    0.80
    Activations Density 0.018%

    No Known Activations