© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    references to legal or governmental entities, such as "Special Tribunal" or "Special Prosecutor"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Special" entities or operations, likely in a legal or military context

    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
    •Special

    No Comments

    Negative Logits
    76561
    -0.76
     Twain
    -0.69
    iHUD
    -0.67
    \\\\\\\\
    -0.67
     Janeiro
    -0.66
    kj
    -0.64
    ILLE
    -0.63
    shown
    -0.63
    gone
    -0.60
     Zurich
    -0.60
    POSITIVE LOGITS
    ised
    1.07
    izations
    1.02
    ized
    0.97
    isations
    0.92
    ties
    0.91
    izes
    0.85
     Ops
    0.84
    ization
    0.83
    ty
    0.79
     counsel
    0.78
    Activations Density 0.020%

    No Known Activations