© 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. 6-RES-JB
    11. 14405
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presentation and importance of factual information

    oai_token-act-pair · gpt-3.5-turbo

    references to facts and their importance in discussions or evaluations

    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
    yss
    -0.87
    osi
    -0.84
    interstitial
    -0.84
    isoft
    -0.81
    rint
    -0.77
    hod
    -0.76
    ovo
    -0.74
    aeper
    -0.72
    ebus
    -0.70
    leased
    -0.70
    POSITIVE LOGITS
    heet
    1.04
    facts
    0.89
    fulness
    0.85
    telling
    0.85
     facts
    0.82
     pertaining
    0.80
     inacc
    0.77
    sheets
    0.76
     surrounding
    0.74
    sheet
    0.74
    Activations Density 0.020%

    No Known Activations