© 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. 4-RES-JB
    11. 13148
    Prev
    Next
    INDEX
    Explanations

    the phrase "sort of" in text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "sort of" used to introduce classifications or descriptions

    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
    BLE
    -0.76
    DS
    -0.73
    arks
    -0.71
    LAN
    -0.69
    BS
    -0.67
    SB
    -0.67
    ishops
    -0.67
    MEN
    -0.66
    WOR
    -0.65
    STER
    -0.64
    POSITIVE LOGITS
    sort
    0.84
    ãĤ¦ãĤ¹
    0.81
    unia
    0.76
    entially
    0.73
     sort
    0.72
     pronouns
    0.72
    ractor
    0.68
     sorting
    0.68
    ilege
    0.68
    urai
    0.66
    Activations Density 0.019%

    No Known Activations