© 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. 3-RES-JB
    11. 10800
    Prev
    Next
    INDEX
    Explanations

    formal statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to formal declarations or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsius
    -0.81
    rys
    -0.75
    osponsors
    -0.72
    axy
    -0.71
    rowd
    -0.71
    versely
    -0.71
    bat
    -0.70
    cffff
    -0.70
    ricular
    -0.69
    engeance
    -0.66
    POSITIVE LOGITS
     statements
    1.09
     statement
    0.90
     pronoun
    0.85
     uttered
    0.85
    gow
    0.79
     Statements
    0.77
    ARB
    0.76
     regarding
    0.75
     warr
    0.75
    Statement
    0.75
    Activations Density 0.026%

    No Known Activations