© 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. 2-RES-JB
    6. 834
    Prev
    Next
    INDEX
    Explanations

    the word 'filming'

    oai_token-act-pair · gpt-4-turbo

    words and phrases related to the act of filming

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of filming or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.80
    undai
    -0.72
    abies
    -0.71
    issue
    -0.70
    alg
    -0.67
    mission
    -0.66
    cup
    -0.66
    dies
    -0.66
    ppard
    -0.65
    diagn
    -0.65
    POSITIVE LOGITS
     filming
    0.93
     filmed
    0.86
     footage
    0.85
     Camer
    0.81
     VIDE
    0.79
    ÃįÃį
    0.75
     tripod
    0.74
    ograp
    0.73
     RAW
    0.72
    rodu
    0.72
    Activations Density 0.021%

    No Known Activations