© 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. 20507
    Prev
    Next
    INDEX
    Explanations

    terms related to smooth transitions or integration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to seamless integration or smooth transitions

    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
    acons
    -0.77
    rared
    -0.72
    prop
    -0.71
    fighters
    -0.69
    severe
    -0.66
    agents
    -0.65
     sincerely
    -0.63
    oft
    -0.63
    enf
    -0.63
     generously
    -0.63
    POSITIVE LOGITS
     transition
    1.06
     transitions
    1.03
     departure
    0.78
     breeze
    0.78
     sailing
    0.77
    going
    0.75
     Transition
    0.72
    ness
    0.70
     continuation
    0.69
     merging
    0.68
    Activations Density 0.084%

    No Known Activations