© 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. 7-RES-JB
    11. 22616
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ation"

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the suffix "ation," indicating processes, actions, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.79
    ãĥ£
    -0.73
    herty
    -0.72
     mosqu
    -0.68
    soDeliveryDate
    -0.68
    ilan
    -0.67
     opio
    -0.66
    tails
    -0.64
    friends
    -0.64
    ãĥĥãĥī
    -0.64
    POSITIVE LOGITS
    ary
    1.52
    ally
    1.30
    naire
    1.22
    ist
    1.17
    aries
    1.17
    hower
    1.09
    arily
    0.99
    eering
    0.98
    ality
    0.97
    ists
    0.96
    Activations Density 0.149%

    No Known Activations