© 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. 7-RES-JB
    11. 23652
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or reflections

    oai_token-act-pair · gpt-3.5-turbo

    references to personal thoughts and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALL
    -0.83
     Mamm
    -0.69
    Availability
    -0.61
    gm
    -0.61
    ARDS
    -0.60
    Claim
    -0.60
    toe
    -0.59
    ards
    -0.57
    Ann
    -0.57
    aud
    -0.57
    POSITIVE LOGITS
     aloud
    0.90
    ileaks
    0.86
    cience
    0.84
    fulness
    0.81
     provoking
    0.81
    ynthesis
    0.78
    peed
    0.78
    cient
    0.77
    mares
    0.77
     thoughts
    0.76
    Activations Density 0.028%

    No Known Activations