© 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. 8-RES-JB
    11. 20335
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time or events occurring over a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aret
    -0.59
    regon
    -0.59
    vation
    -0.59
    irie
    -0.58
    minster
    -0.56
    rote
    -0.56
    origin
    -0.56
    odium
    -0.56
    uala
    -0.55
    ryn
    -0.55
    POSITIVE LOGITS
    opian
    0.80
    ivist
    0.76
    course
    0.75
     weeks
    0.72
    tenance
    0.68
    cible
    0.66
     thereof
    0.65
    rest
    0.65
    waters
    0.63
     of
    0.63
    Activations Density 0.017%

    No Known Activations