© 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. 7-RES-JB
    11. 12444
    Prev
    Next
    INDEX
    Explanations

    verbs with 'ing'suffix that involve some sort of action or process

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to assertion and prediction

    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
    avorite
    -0.76
     Solitaire
    -0.67
     impulse
    -0.65
     felon
    -0.65
    RAW
    -0.64
     Forever
    -0.64
     bye
    -0.63
     curfew
    -0.63
     uncontroll
    -0.63
     americ
    -0.62
    POSITIVE LOGITS
    aled
    1.06
    ighed
    1.05
    ving
    1.02
    istered
    1.02
    ues
    1.01
    oused
    1.00
    uing
    0.99
    arding
    0.99
    ued
    0.98
    aling
    0.97
    Activations Density 0.235%

    No Known Activations