© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9165
    Prev
    Next
    INDEX
    Explanations

    phrases related to assertive statements

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various forms and usages

    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
    ilst
    -0.72
     Achieve
    -0.71
    iates
    -0.71
    udeau
    -0.68
    atives
    -0.66
     accuses
    -0.65
    ipient
    -0.63
    osate
    -0.63
     Sources
    -0.62
     alleges
    -0.61
    POSITIVE LOGITS
     gonna
    1.30
    nt
    1.15
     ALWAYS
    1.12
     definitely
    1.06
     always
    0.97
    senal
    0.96
     probably
    0.95
     kinda
    0.95
     amazing
    0.92
     supposed
    0.91
    Activations Density 0.556%

    No Known Activations