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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17644
    Prev
    Next
    INDEX
    Explanations

    references to a specific item or concept that has the name "ico" with various activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ico," likely related to the concept of "iconic" or "iconography."

    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
    ting
    -0.81
    gling
    -0.80
    stall
    -0.75
    luck
    -0.74
    mable
    -0.72
    itarian
    -0.70
    lessly
    -0.69
    sworth
    -0.69
    âķIJâķIJ
    -0.66
    lihood
    -0.66
    POSITIVE LOGITS
    zzi
    1.10
    verage
    0.87
    zzle
    0.82
    atl
    0.82
    ffee
    0.80
    kefeller
    0.78
    cephal
    0.75
    leans
    0.74
    ourt
    0.73
    igne
    0.73
    Activations Density 0.026%

    No Known Activations