© 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. 19722
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that may involve conflict, investigation, physical disruption, or heated interactions

    oai_token-act-pair · gpt-3.5-turbo

    past participles of verbs

    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
    tis
    -0.69
    eda
    -0.68
    held
    -0.62
    adra
    -0.62
    stack
    -0.60
    thur
    -0.60
    oter
    -0.58
     [+]
    -0.58
     weighed
    -0.57
    ansk
    -0.55
    POSITIVE LOGITS
    nesday
    0.81
    ieval
    0.76
    dit
    0.75
     extensively
    0.74
     havoc
    0.72
    adoes
    0.69
    imentary
    0.67
    rome
    0.67
    Downloadha
    0.66
    roid
    0.65
    Activations Density 0.155%

    No Known Activations