© 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. 17929
    Prev
    Next
    INDEX
    Explanations

    technical instructions or steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting instructions or steps in a process

    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
    SPONSORED
    -1.02
     âĢ¦"
    -0.74
    âĢ¦."
    -0.68
     ****
    -0.68
    sic
    -0.67
     Malfoy
    -0.64
    âĢ¦"
    -0.64
    âĸł
    -0.62
    ..."
    -0.61
    -"
    -0.60
    POSITIVE LOGITS
     simplest
    0.87
    orically
    0.78
    withstanding
    0.77
    merce
    0.76
    iage
    0.75
     easiest
    0.72
    resa
    0.70
    ensibly
    0.70
    ritis
    0.70
    hester
    0.69
    Activations Density 0.407%

    No Known Activations