© 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. 9513
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to intensity or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sheer" and other adjectives indicating extremity or intensity

    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
    anwhile
    -0.77
    ublic
    -0.74
    afort
    -0.74
    atern
    -0.71
    SHIP
    -0.70
    acterial
    -0.70
    microsoft
    -0.67
    cients
    -0.67
    istant
    -0.67
    lict
    -0.66
    POSITIVE LOGITS
     sheer
    1.11
     unbeliev
    0.87
    ãĤ¨ãĥ«
    0.82
     enorm
    0.81
     volume
    0.78
    catentry
    0.78
    ãĤ¦ãĤ¹
    0.76
    odox
    0.75
     simplicity
    0.75
     coincidence
    0.71
    Activations Density 0.007%

    No Known Activations