Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21044
    Prev
    Next
    INDEX
    Explanations

    specific mentions of computer-generated text markers, such as

    oai_token-act-pair · gpt-3.5-turbo

    geographic and political references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.68
     comprom
    -0.61
    figure
    -0.61
    cation
    -0.61
    avez
    -0.60
    fight
    -0.59
     lapse
    -0.59
    issan
    -0.57
    pressure
    -0.57
    raints
    -0.57
    POSITIVE LOGITS
    emetery
    0.97
     referen
    0.93
     redes
    0.77
    aeper
    0.75
    TPPStreamerBot
    0.74
    ocument
    0.73
    PDATE
    0.70
    GGGGGGGG
    0.68
    mercial
    0.68
    estones
    0.67
    Activations Density 7.262%

    No Known Activations