© 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. 6-RES-JB
    11. 1652
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or dealings

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the context of time or specific temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.73
    itched
    -0.65
    ashtra
    -0.65
    ascular
    -0.63
    hovah
    -0.62
    steen
    -0.60
    ifted
    -0.60
    iour
    -0.59
    nown
    -0.58
     Nicotine
    -0.57
    POSITIVE LOGITS
    estone
    0.64
     Tre
    0.63
    è¯
    0.61
    upon
    0.61
    aceous
    0.58
    ordinate
    0.57
    maid
    0.57
    estones
    0.57
     Republic
    0.56
     Sor
    0.56
    Activations Density 0.365%

    No Known Activations