Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8528
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a change or shift from one thing to another

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to transitions or shifts, particularly in systems or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earthquakes
    -0.66
    $$
    -0.66
    icious
    -0.63
     Enough
    -0.62
    awar
    -0.59
    eatures
    -0.58
    phies
    -0.57
    umni
    -0.56
     Inside
    -0.56
     deserve
    -0.55
    POSITIVE LOGITS
    odox
    0.89
     simpler
    0.84
     alternatives
    0.84
    usterity
    0.83
     cheaper
    0.83
     mode
    0.82
     cheapest
    0.81
     approach
    0.79
    luaj
    0.79
     narrower
    0.76
    Activations Density 0.502%

    No Known Activations