© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations or charges in a legal context

    oai_token-act-pair · gpt-3.5-turbo

    references to allegations and their 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
    Not in Any Lists

    No Comments

    Negative Logits
    keys
    -0.79
     busiest
    -0.74
    oppy
    -0.69
    tz
    -0.68
    å¸
    -0.67
    ARCH
    -0.66
    skill
    -0.65
    arton
    -0.64
    patch
    -0.64
     stocking
    -0.63
    POSITIVE LOGITS
     allegations
    1.12
     accusation
    1.01
     accusations
    1.00
     alleging
    0.99
     allegation
    0.99
     alleges
    0.95
     accusing
    0.92
     levied
    0.92
     leveled
    0.90
     leve
    0.87
    Activations Density 0.039%

    No Known Activations