© 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. 22507
    Prev
    Next
    INDEX
    Explanations

    phrases describing various actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of existence or presence in statements

    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
     Pants
    -0.67
     TRUMP
    -0.64
    ingham
    -0.62
    abases
    -0.61
    essen
    -0.59
    asketball
    -0.58
     RG
    -0.57
    emate
    -0.57
    equality
    -0.56
    cha
    -0.56
    POSITIVE LOGITS
     wont
    1.04
     evidenced
    0.83
     attest
    0.74
     often
    0.71
     [|
    0.69
    çĶ°
    0.68
    ãĥĩãĤ£
    0.67
     tremend
    0.67
     actionGroup
    0.67
     previously
    0.67
    Activations Density 0.220%

    No Known Activations