© 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. 4-RES-JB
    11. 19454
    Prev
    Next
    INDEX
    Explanations

    references to reflective surfaces or metaphors in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to "mirror" and its various forms

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

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.76
    erest
    -0.73
    ordes
    -0.72
    stant
    -0.72
    ensable
    -0.71
    cific
    -0.70
    reek
    -0.69
    roup
    -0.69
    AFTA
    -0.68
    amily
    -0.68
    POSITIVE LOGITS
    ror
    0.97
     Mirror
    0.91
     mirror
    0.91
     neuron
    0.83
     shine
    0.83
     reflection
    0.81
    ocular
    0.77
     mirrors
    0.77
    pool
    0.76
     reflections
    0.76
    Activations Density 0.011%

    No Known Activations