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

    Neuronpedia

    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. 8-RES-JB
    11. 3230
    Prev
    Next
    INDEX
    Explanations

    terms or acronyms related to specific institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions or organizations, particularly those related to nuclear energy and banking

    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
    lets
    -0.76
     Brach
    -0.76
    Äĩ
    -0.70
    auri
    -0.68
    rief
    -0.67
    letes
    -0.66
    rooms
    -0.66
    ãĤª
    -0.65
    imore
    -0.65
    ongyang
    -0.65
    POSITIVE LOGITS
    OVA
    1.23
    FOR
    1.23
    TERN
    1.20
    PUT
    1.18
    ROR
    1.08
    IST
    1.07
    NER
    1.06
    VEN
    1.06
    ET
    1.05
    FER
    1.04
    Activations Density 0.080%

    No Known Activations