© 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
    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. 7712
    Prev
    Next
    INDEX
    Explanations

    mention of film, television, or other media production companies

    oai_token-act-pair · gpt-3.5-turbo

    references to production companies in the context of film and television

    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
     Ike
    -0.76
    usable
    -0.75
    rounded
    -0.74
     usable
    -0.72
    hots
    -0.66
    itatively
    -0.66
    BILITY
    -0.66
     OECD
    -0.64
     Kobe
    -0.64
    comfort
    -0.63
    POSITIVE LOGITS
     Productions
    2.95
     Films
    1.89
     Presents
    1.74
     productions
    1.37
     Records
    1.33
     imprint
    1.20
     Publications
    1.16
     Enterprises
    1.11
     Publishing
    1.10
    istries
    1.07
    Activations Density 0.039%

    No Known Activations