© 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. 3623
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or entity named "Crystal"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Crystal," likely indicating a focus on locations or entities associated with that name

    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
    alach
    -0.82
    ahime
    -0.81
    went
    -0.78
    ername
    -0.78
    nir
    -0.77
    aciously
    -0.76
    orship
    -0.76
    respons
    -0.71
    entimes
    -0.70
    enegger
    -0.69
    POSITIVE LOGITS
     Palace
    1.11
     Maiden
    1.10
     Springs
    1.00
     Gems
    0.91
     Fey
    0.83
    pler
    0.80
    stals
    0.80
    stal
    0.79
     Lake
    0.79
     Crystal
    0.77
    Activations Density 0.014%

    No Known Activations