© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 771
    Prev
    Next
    INDEX
    Explanations

    terms related to the box office and financial performance of films

    oai_token-act-pair · gpt-3.5-turbo

    terms related to box office performance and financial metrics in the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.87
     Jem
    -0.84
    amber
    -0.70
    etheless
    -0.66
    eworld
    -0.66
    imore
    -0.65
    ivas
    -0.65
    lime
    -0.64
    itudinal
    -0.61
     Loving
    -0.61
    POSITIVE LOGITS
     calculation
    0.87
     calculations
    0.84
    utra
    0.84
     projections
    0.81
    aminer
    0.80
     estimation
    0.78
     estimates
    0.78
     totals
    0.77
     savings
    0.77
     coffers
    0.76
    Activations Density 0.130%

    No Known Activations