© 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. 4-RES-JB
    11. 6607
    Prev
    Next
    INDEX
    Explanations

    terms related to ions and ionization

    oai_token-act-pair · gpt-3.5-turbo

    references to ions and ionic processes

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

    No Comments

    Negative Logits
    EEK
    -0.91
    RESULTS
    -0.84
    ĻĤ
    -0.81
    ORD
    -0.80
    é¾įå¥ij士
    -0.76
     Horror
    -0.76
    Aust
    -0.74
    EY
    -0.72
    MY
    -0.71
     Fargo
    -0.71
    POSITIVE LOGITS
    ucl
    1.08
    osphere
    1.01
     ion
    0.95
    osp
    0.89
    ometric
    0.87
    ically
    0.86
    ogical
    0.86
    ysis
    0.85
    ially
    0.84
    ium
    0.83
    Activations Density 0.007%

    No Known Activations