© 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. 7-RES-JB
    11. 24018
    Prev
    Next
    INDEX
    Explanations

    negative or skeptical statements

    oai_token-act-pair · gpt-3.5-turbo

    negations and indicators of absence or insufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DNA
    -0.81
    RNA
    -0.79
    BuyableInstoreAndOnline
    -0.78
    Champ
    -0.78
    adium
    -0.78
    ãĤ´ãĥ³
    -0.76
    VO
    -0.71
    ruct
    -0.70
    dress
    -0.70
    gage
    -0.70
    POSITIVE LOGITS
     accordingly
    1.22
     consequently
    1.08
     consequ
    0.97
     moreover
    0.93
     furthermore
    0.86
     therefore
    0.85
     thence
    0.84
     doubtless
    0.82
     therein
    0.81
    etheless
    0.80
    Activations Density 0.436%

    No Known Activations