© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2634
    Prev
    Next
    INDEX
    Explanations

    a specific type of structure or system, possibly related to instructions or processes involving various components

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oids
    -0.58
    ings
    -0.55
    outs
    -0.55
    rates
    -0.53
    bars
    -0.53
     these
    -0.52
    aways
    -0.51
     besides
    -0.51
    ody
    -0.51
    killers
    -0.50
    POSITIVE LOGITS
    usterity
    0.60
    venge
    0.59
    rouse
    0.58
     bunch
    0.56
    sexual
    0.55
     nutshell
    0.55
     lot
    0.54
    uras
    0.54
     prostitute
    0.54
     typo
    0.54
    Activations Density 0.548%

    No Known Activations