© 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. 6237
    Prev
    Next
    INDEX
    Explanations

    instances where help is needed or sought after

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "help" 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
    theless
    -0.73
    ross
    -0.69
    Pict
    -0.68
    andom
    -0.67
    ategory
    -0.67
    ModLoader
    -0.65
     rall
    -0.63
     Bulg
    -0.62
     Rim
    -0.62
    é¾
    -0.59
    POSITIVE LOGITS
    fully
    1.03
    des
    1.00
     Desk
    0.94
    meet
    0.87
    ful
    0.79
    full
    0.73
     desk
    0.72
    ocating
    0.72
    fulness
    0.72
    Desk
    0.70
    Activations Density 0.047%

    No Known Activations