© 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 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. 6-RES-JB
    11. 8478
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone not having the authority or suitability for a particular action or position

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "business" or the legitimacy of actions and choices

    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
    HEAD
    -0.67
    visor
    -0.65
     Dane
    -0.63
     Ribbon
    -0.63
     Sig
    -0.59
    ahime
    -0.59
    nee
    -0.58
    ipple
    -0.57
     Signal
    -0.57
     hailed
    -0.57
    POSITIVE LOGITS
     whatsoever
    1.73
     anymore
    0.98
     nor
    0.94
    Ö¼
    0.74
     earthly
    0.71
    ocracy
    0.69
     affiliation
    0.67
     slightest
    0.67
     except
    0.66
     besides
    0.66
    Activations Density 0.146%

    No Known Activations