© 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. 7-RES-JB
    11. 17122
    Prev
    Next
    INDEX
    Explanations

    phrases related to assessing products or services for value and potential improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to product valuation and marketing strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.72
    prison
    -0.62
     Nichols
    -0.59
    sections
    -0.59
    nsic
    -0.58
     Hornets
    -0.58
     prosecutions
    -0.58
     whistleblower
    -0.57
     watchdog
    -0.57
     Pratt
    -0.56
    POSITIVE LOGITS
    worthiness
    0.79
     etc
    0.79
     blah
    0.68
    vironment
    0.68
    Quantity
    0.67
     XY
    0.67
    worthy
    0.67
    omever
    0.65
    acebook
    0.64
     goodness
    0.64
    Activations Density 1.443%

    No Known Activations