© 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. 10-RES-JB
    11. 2636
    Prev
    Next
    INDEX
    Explanations

    instances where something is unable to be done or accomplished

    oai_token-act-pair · gpt-3.5-turbo

    negation expressions indicating inability or lack of capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.85
    azard
    -0.77
    CI
    -0.71
    soType
    -0.70
    meier
    -0.65
    heavy
    -0.61
    DragonMagazine
    -0.60
     Kills
    -0.60
    fee
    -0.60
     privile
    -0.59
    POSITIVE LOGITS
     afford
    1.48
     cope
    1.38
     comprehend
    1.19
     tolerate
    1.14
     muster
    1.12
     conceive
    1.10
    athom
    1.07
     distinguish
    1.07
     stomach
    1.06
     withstand
    1.06
    Activations Density 0.113%

    No Known Activations