© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal incidents and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" and its occurrences in the text

    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
    ingly
    -0.81
    omics
    -0.76
    liam
    -0.75
    loads
    -0.71
    quished
    -0.68
    ivably
    -0.68
    rand
    -0.68
     wisely
    -0.67
    wart
    -0.67
    Å¡
    -0.67
    POSITIVE LOGITS
     latter
    1.32
     same
    1.12
     incident
    1.12
     alleged
    1.08
     aforementioned
    1.03
     entire
    1.01
     ensuing
    1.01
     remainder
    0.99
     contents
    0.99
     offending
    0.97
    Activations Density 0.860%

    No Known Activations