© 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. 8-RES-JB
    11. 23387
    Prev
    Next
    INDEX
    Explanations

    jewelry-related terms

    oai_token-act-pair · gpt-3.5-turbo

    word forms that indicate specific types of food or dietary elements

    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
    atform
    -0.76
     CFR
    -0.73
    ADRA
    -0.69
    abase
    -0.61
     mov
    -0.60
    achus
    -0.59
    umbered
    -0.57
    catentry
    -0.57
     reversible
    -0.56
     arrang
    -0.56
    POSITIVE LOGITS
     heights
    0.71
    orius
    0.69
    hani
    0.66
    ¿
    0.65
    ito
    0.64
    aman
    0.64
    aiden
    0.63
    acha
    0.63
    rock
    0.63
    cki
    0.63
    Activations Density 0.153%

    No Known Activations