© 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. 0-RES-JB
    11. 6833
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'Charter'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization named "Charter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igl
    -0.79
    rm
    -0.75
    theless
    -0.69
     finger
    -0.67
     fingert
    -0.65
     figur
    -0.65
    oids
    -0.64
    urally
    -0.63
     flask
    -0.63
    ply
    -0.63
    POSITIVE LOGITS
     Charter
    4.23
     charter
    1.82
     Constitution
    1.02
     Treaty
    1.00
     Comcast
    0.93
     Chamberlain
    0.93
     Declaration
    0.93
     Cable
    0.91
     Telecommunications
    0.91
     Clause
    0.90
    Activations Density 0.007%

    No Known Activations