© 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. 8-RES-JB
    11. 8340
    Prev
    Next
    INDEX
    Explanations

    verbs followed by a word relating to the senses or feelings, such as "feeling", "see", or "hear"

    oai_token-act-pair · gpt-3.5-turbo

    common auxiliary and state verbs indicating existence or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COURT
    -0.67
    peak
    -0.65
     Palestin
    -0.63
     suspic
    -0.59
     deadliest
    -0.58
    elligence
    -0.56
     Maver
    -0.56
     stride
    -0.56
     DISTRICT
    -0.56
     Yose
    -0.56
    POSITIVE LOGITS
    able
    0.93
    ables
    0.89
    eth
    0.88
    ings
    0.83
    ingly
    0.82
    gal
    0.78
    inates
    0.76
    abouts
    0.75
    nings
    0.75
    ls
    0.74
    Activations Density 0.318%

    No Known Activations