© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    common phrases starting with "a" and "and"

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    ernels
    -0.91
    lems
    -0.89
    lees
    -0.77
     Machines
    -0.76
    nces
    -0.72
    Ĥİ
    -0.71
    profits
    -0.71
    psc
    -0.70
    MET
    -0.69
     Accounts
    -0.69
    POSITIVE LOGITS
    ogram
    0.86
     reader
    0.78
    ressor
    0.78
     haircut
    0.74
     apology
    0.74
    ograph
    0.73
     arrangement
    0.72
     standpoint
    0.72
     diploma
    0.71
     converter
    0.70
    Activations Density 0.342%

    No Known Activations