© 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. 2-RES-JB
    11. 12817
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of formalization or standardization

    oai_token-act-pair · gpt-3.5-turbo

    words that end with the suffix "ised" indicating processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PHOTOS
    -0.65
    女
    -0.63
     Dull
    -0.61
    idian
    -0.60
    aida
    -0.59
    PU
    -0.58
    ilan
    -0.58
    iology
    -0.58
    print
    -0.58
    900
    -0.57
    POSITIVE LOGITS
    ises
    0.85
    ablishment
    0.84
    ising
    0.82
    ised
    0.82
    ise
    0.80
    isation
    0.78
    uminium
    0.76
    anchester
    0.74
    inburgh
    0.73
    iser
    0.72
    Activations Density 0.024%

    No Known Activations