© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17292
    Prev
    Next
    INDEX
    Explanations

    phrases indicating fitting or compatibility with a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating compatibility or fitting within contexts or categories

    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
    heny
    -0.69
    wl
    -0.61
    pora
    -0.60
     Dhabi
    -0.60
     Accessed
    -0.59
    alcohol
    -0.57
    gov
    -0.57
    xious
    -0.57
    matter
    -0.56
    casters
    -0.56
    POSITIVE LOGITS
     precon
    0.79
     stereotype
    0.76
    ãĤ¤ãĥĪ
    0.71
    Position
    0.70
     bounds
    0.70
    Interstitial
    0.67
     criteria
    0.65
     stereotypes
    0.65
    oin
    0.65
     stereotypical
    0.64
    Activations Density 0.155%

    No Known Activations