© 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. 10-RES-JB
    11. 14149
    Prev
    Next
    INDEX
    Explanations

    words related to reflection or mirroring

    oai_token-act-pair · gpt-3.5-turbo

    references to mirrors and mirror imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.80
    CVE
    -0.74
    ensable
    -0.74
    stant
    -0.71
    ndra
    -0.70
    ties
    -0.69
    estern
    -0.68
    iott
    -0.67
    iencies
    -0.67
    tions
    -0.66
    POSITIVE LOGITS
    ror
    1.02
     neuron
    1.00
    ocular
    0.96
     image
    0.95
     mirror
    0.88
    angelo
    0.87
     reflection
    0.87
    image
    0.86
     Mirror
    0.86
     images
    0.85
    Activations Density 0.033%

    No Known Activations