© 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. 511
    Prev
    Next
    INDEX
    Explanations

    phrases related to synthesis or synthesizing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to synthesis and synthesizers

    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
    entity
    -0.71
     Redemption
    -0.67
    den
    -0.67
    Reviewer
    -0.67
     Peninsula
    -0.66
    onne
    -0.64
    Virgin
    -0.64
     Humane
    -0.63
    Bull
    -0.63
    GF
    -0.61
    POSITIVE LOGITS
     synthes
    1.09
     synthesis
    1.01
    entanyl
    0.94
    ivity
    0.84
    ationally
    0.83
    ically
    0.83
    izer
    0.82
    alysis
    0.82
    iasco
    0.81
    izers
    0.80
    Activations Density 0.008%

    No Known Activations