© 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. 13940
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "nothingness" or lack of value

    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
    circ
    -0.71
    assis
    -0.69
    amic
    -0.68
    asio
    -0.67
    grad
    -0.67
    roc
    -0.66
    mart
    -0.64
    opal
    -0.64
     rooft
    -0.61
    ros
    -0.61
    POSITIVE LOGITS
     else
    1.13
    Else
    1.03
     imaginable
    0.86
     conceivable
    0.86
    ĸļ
    0.83
     whatsoever
    0.83
    soever
    0.83
    THING
    0.81
     extravagant
    0.76
    ĪĴ
    0.75
    Activations Density 0.018%

    No Known Activations