© 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. 6-RES-JB
    11. 11600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack or absence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "None"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bledon
    -0.73
     widest
    -0.69
     guiActiveUnfocused
    -0.68
    cum
    -0.67
    rod
    -0.64
    roit
    -0.63
    romy
    -0.63
    ciation
    -0.60
    nas
    -0.60
    pu
    -0.60
    POSITIVE LOGITS
    essee
    0.97
     Detected
    0.82
    lect
    0.79
    theless
    0.73
    etting
    0.72
    uther
    0.72
    orem
    0.71
     Ended
    0.70
    conom
    0.67
     sane
    0.67
    Activations Density 0.010%

    No Known Activations