© 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. 8-RES-JB
    11. 18568
    Prev
    Next
    INDEX
    Explanations

    verbs expressing capability or potential

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "can" and its negation "can't"

    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
     Falling
    -0.64
    senal
    -0.64
    ULTS
    -0.60
    soever
    -0.60
     fav
    -0.60
     Sod
    -0.60
     Actions
    -0.59
     Expend
    -0.57
     Flags
    -0.57
     Eur
    -0.56
    POSITIVE LOGITS
    't
    1.29
     afford
    1.29
     convince
    1.01
     muster
    0.93
     persuade
    0.90
     manage
    0.88
    utils
    0.86
     reliably
    0.86
     help
    0.84
    adian
    0.83
    Activations Density 0.134%

    No Known Activations