© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    phrases related to proof of concept and holding securities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to proof concepts and their implications

    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
    adelphia
    -0.75
    scape
    -0.66
    bleacher
    -0.66
    netflix
    -0.65
     ILCS
    -0.64
    erest
    -0.64
    lance
    -0.64
    _-
    -0.62
    atorium
    -0.62
     Frazier
    -0.61
    POSITIVE LOGITS
     existence
    0.88
    concept
    0.78
     authenticity
    0.69
     occupancy
    0.69
     equival
    0.68
     principle
    0.67
     nonex
    0.67
     correctness
    0.66
     efficacy
    0.65
     completion
    0.65
    Activations Density 0.054%

    No Known Activations