© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 9600
    Prev
    Next
    INDEX
    Explanations

    phrases related to accepting or acceptance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iferation
    -0.79
    brow
    -0.76
    etsk
    -0.73
    borgh
    -0.73
     glands
    -0.70
    vic
    -0.70
    ghazi
    -0.67
    geist
    -0.66
    vertisement
    -0.65
    ffield
    -0.65
    POSITIVE LOGITS
     accept
    0.88
    ably
    0.86
     accepting
    0.84
     acceptance
    0.83
    ances
    0.82
     responsibility
    0.79
    ANCE
    0.77
     accepted
    0.77
     Accept
    0.76
     bribes
    0.74
    Activations Density 0.035%

    No Known Activations