© 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. 21791
    Prev
    Next
    INDEX
    Explanations

    words related to actions or states of being, focusing on the verb form

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or states of being

    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
     COURT
    -0.74
     Palestin
    -0.65
     suspic
    -0.64
    elligence
    -0.63
     DISTRICT
    -0.63
    avorite
    -0.63
    peak
    -0.61
     mosqu
    -0.60
     stride
    -0.58
     deadliest
    -0.57
    POSITIVE LOGITS
    able
    1.01
    ings
    0.94
    eth
    0.91
    ables
    0.90
    ingly
    0.89
    backs
    0.83
    ties
    0.82
    ances
    0.82
    zeb
    0.80
    runs
    0.77
    Activations Density 0.381%

    No Known Activations