© 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. 6811
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific durations of time

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and its various contexts

    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
    dal
    -0.65
    agically
    -0.64
    sym
    -0.62
    resa
    -0.61
    Sym
    -0.61
     Reincarn
    -0.61
    tailed
    -0.60
    lys
    -0.60
     destro
    -0.60
     bitters
    -0.59
    POSITIVE LOGITS
    ifiable
    1.11
    ifications
    0.84
    inian
    0.72
    ovic
    0.71
     FY
    0.68
     basics
    0.67
     plain
    0.64
    othing
    0.61
    itia
    0.60
     mortals
    0.59
    Activations Density 0.045%

    No Known Activations