© 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. 8-RES-JB
    11. 5038
    Prev
    Next
    INDEX
    Explanations

    words related to challenges or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    the word "because" indicating reasons or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hal
    -0.76
    lez
    -0.72
     exting
    -0.70
    nin
    -0.69
    agin
    -0.66
    shaw
    -0.66
    ax
    -0.66
    alin
    -0.66
    ses
    -0.66
    fml
    -0.64
    POSITIVE LOGITS
     they
    0.87
     unlike
    0.84
     there
    0.84
    */(
    0.80
     it
    0.78
     nobody
    0.73
     we
    0.70
     oft
    0.67
     otherwise
    0.67
     successive
    0.65
    Activations Density 0.082%

    No Known Activations