© 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. 9-RES-JB
    11. 1381
    Prev
    Next
    INDEX
    Explanations

    specific characters that likely have special significance or formatting marks within the text

    oai_token-act-pair · gpt-3.5-turbo

    isolated segments of text, indicating a focus on key phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gren
    -0.61
     secondly
    -0.59
     agility
    -0.59
     occasional
    -0.57
     Secondly
    -0.56
     undecided
    -0.56
    gold
    -0.55
    milo
    -0.55
    sheets
    -0.55
    frames
    -0.54
    POSITIVE LOGITS
    Interested
    0.88
    arta
    0.80
    SHARE
    0.79
    WASHINGTON
    0.77
    SEE
    0.76
    Amid
    0.71
    ³³³³
    0.71
    Writing
    0.70
    Actor
    0.70
    PROV
    0.69
    Activations Density 0.315%

    No Known Activations