© 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. 19721
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to recognizing or making something visually or conceptually

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "out."

    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
    inki
    -0.83
     upgr
    -0.71
    iets
    -0.68
    ahime
    -0.67
    phrine
    -0.65
     progression
    -0.64
    vernment
    -0.62
     awa
    -0.62
    avorite
    -0.62
     Decay
    -0.61
    POSITIVE LOGITS
    casts
    0.94
    pieces
    0.77
    posts
    0.77
    cast
    0.77
    acular
    0.72
    landish
    0.72
    âĶģ
    0.66
    fitted
    0.65
     *)
    0.65
    URES
    0.65
    Activations Density 0.047%

    No Known Activations