© 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. 0-RES-JB
    6. 23262
    Prev
    Next
    INDEX
    Explanations

    references to the filmmaker Ridley Scott

    oai_token-act-pair · gpt-3.5-turbo

    references to the director Ridley Scott and his film Prometheus

    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
    oba
    -0.76
    zan
    -0.67
     jug
    -0.65
     Stro
    -0.65
     cup
    -0.65
     span
    -0.63
     en
    -0.62
     Operations
    -0.61
     bus
    -0.61
     Calder
    -0.60
    POSITIVE LOGITS
     Ridley
    4.58
     Prometheus
    1.33
     Metroid
    1.23
     Locke
    1.19
     Tid
    1.14
    imeo
    1.13
     Pruitt
    1.08
     Lowe
    1.06
     Bruno
    1.04
     Bridgewater
    1.03
    Activations Density 0.053%

    No Known Activations