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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7563
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions and statements made in formal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions or statements made in an academic or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhabit
    -0.69
     excel
    -0.68
     Hath
    -0.65
     protagonists
    -0.64
    inav
    -0.64
     pioneer
    -0.64
     powerhouse
    -0.64
     flock
    -0.63
     Notting
    -0.63
     traveller
    -0.63
    POSITIVE LOGITS
     permissible
    1.14
     confidential
    1.05
     consensual
    1.04
     inappropriate
    1.03
     pending
    1.03
     unrelated
    1.02
     moot
    1.01
     untrue
    1.00
     precaution
    1.00
     unnecessary
    1.00
    Activations Density 0.376%

    No Known Activations