© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10782
    Prev
    Next
    INDEX
    Explanations

    numbers related to energy production and consumption

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to energy and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gould
    -0.64
     Leilan
    -0.63
     holiest
    -0.63
     tradition
    -0.62
     Companion
    -0.61
     contest
    -0.61
     marqu
    -0.61
     lax
    -0.61
     Situation
    -0.59
     Investor
    -0.59
    POSITIVE LOGITS
    abytes
    1.24
    pees
    1.24
    awatts
    1.13
    ms
    1.07
    bps
    1.04
    rams
    1.02
    mol
    1.01
    pm
    0.95
    pg
    0.94
    bp
    0.93
    Activations Density 0.077%

    No Known Activations