© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1297
    Prev
    Next
    INDEX
    Explanations

    phrases indicating there is more to a situation than what is initially visible or known

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a minor aspect of a larger issue

    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
    iors
    -0.76
    Merit
    -0.70
    forts
    -0.69
    ials
    -0.68
    owship
    -0.66
    ãĤ¹ãĥĪ
    -0.66
    BAT
    -0.65
    except
    -0.65
    FACE
    -0.65
    fy
    -0.64
    POSITIVE LOGITS
     iceberg
    1.25
     scales
    0.82
     scale
    0.72
     finger
    0.70
     toes
    0.70
     rope
    0.69
     Scale
    0.67
     needles
    0.62
    gall
    0.62
     toe
    0.61
    Activations Density 0.092%

    No Known Activations