© 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. 2-RES-JB
    11. 8263
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where the phrase "kind of" is used

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.64
    ħĭ
    -0.61
    ilyn
    -0.60
     ende
    -0.59
     appraisal
    -0.58
     pige
    -0.57
     claws
    -0.57
    nets
    -0.57
     slump
    -0.56
     reperto
    -0.56
    POSITIVE LOGITS
     luck
    0.74
    EVA
    0.72
    icial
    0.69
    ITNESS
    0.68
     course
    0.65
     things
    0.65
    THING
    0.64
    ordinary
    0.64
    Variable
    0.64
     JUSTICE
    0.63
    Activations Density 0.369%

    No Known Activations