© 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. 20421
    Prev
    Next
    INDEX
    Explanations

    phrases related to film studios

    oai_token-act-pair · gpt-3.5-turbo

    references to film studios and productions

    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
    brance
    -0.72
    statement
    -0.71
    pair
    -0.70
    eanor
    -0.60
    worker
    -0.59
    entity
    -0.59
     trait
    -0.59
    Result
    -0.58
     item
    -0.58
     ÏĦ
    -0.58
    POSITIVE LOGITS
     studios
    4.05
     Studios
    2.09
     studio
    1.92
     Studio
    1.58
     labs
    1.51
     theaters
    1.49
     offices
    1.45
     publishers
    1.44
    Studio
    1.39
     productions
    1.38
    Activations Density 0.018%

    No Known Activations