© 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. 1-RES-JB
    11. 8028
    Prev
    Next
    INDEX
    Explanations

    Occurences of the word "kins" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "kins," indicating a focus on familial or relational connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.65
     AQ
    -0.64
    ħĭ
    -0.64
     SIG
    -0.64
    ľ
    -0.61
    Ķ
    -0.60
    ntil
    -0.60
     Fundamental
    -0.60
     duplication
    -0.59
     PM
    -0.59
    POSITIVE LOGITS
    kins
    1.53
    kie
    1.18
    kin
    1.12
    hip
    1.06
    haw
    1.00
    kies
    0.98
    creen
    0.96
    hips
    0.96
    ettes
    0.95
    pring
    0.95
    Activations Density 0.007%

    No Known Activations