© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17993
    Prev
    Next
    INDEX
    Explanations

    the phrase "all sorts of"

    oai_token-act-pair · gpt-3.5-turbo

    references to types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ce
    -0.62
     nor
    -0.61
    HD
    -0.60
    Led
    -0.59
    acher
    -0.58
    bal
    -0.58
    CL
    -0.57
    pa
    -0.56
    Eye
    -0.55
    urd
    -0.55
    POSITIVE LOGITS
     sorts
    4.24
     kinds
    2.44
     sort
    1.84
     kind
    1.48
     types
    1.41
    sort
    1.08
     proportions
    0.99
     type
    0.97
     kinda
    0.94
     Sort
    0.94
    Activations Density 0.010%

    No Known Activations