© 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. 6-RES-JB
    11. 21890
    Prev
    Next
    INDEX
    Explanations

    verbs related to stopping or ceasing an action

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with ceasing or stopping activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anan
    -0.76
    ificent
    -0.74
    ixtures
    -0.71
     glim
    -0.70
     somew
    -0.69
    auld
    -0.67
    egu
    -0.66
    iewicz
    -0.65
    acht
    -0.64
    soType
    -0.64
    POSITIVE LOGITS
     altogether
    1.35
     anymore
    1.07
     entirely
    0.97
     nor
    0.86
    ãĤ®
    0.84
     interruption
    0.79
     whatsoever
    0.78
     Cheong
    0.75
     inhib
    0.74
     unless
    0.73
    Activations Density 0.524%

    No Known Activations