© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    phrases that start with 'along with'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "along with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    wrong
    -0.80
    orius
    -0.77
    iland
    -0.74
    ager
    -0.71
    close
    -0.68
    eri
    -0.68
    mil
    -0.67
    omorphic
    -0.66
    ade
    -0.65
    oren
    -0.65
    POSITIVE LOGITS
     regards
    0.79
     others
    0.76
     countless
    0.73
     other
    0.73
     regard
    0.72
     assorted
    0.72
     dozens
    0.71
     impunity
    0.71
     those
    0.71
     Sakuya
    0.69
    Activations Density 0.052%

    No Known Activations