© 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. 4-RES-JB
    11. 2843
    Prev
    Next
    INDEX
    Explanations

    companies and financial terms related to mergers, acquisitions, and investments

    oai_token-act-pair · gpt-3.5-turbo

    corporate entities and their associated ownership or affiliations

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

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.81
    genre
    -0.76
     Primal
    -0.72
    imester
    -0.69
    pmwiki
    -0.68
     readings
    -0.68
    itarian
    -0.68
     accompan
    -0.68
     symptoms
    -0.67
     chilling
    -0.67
    POSITIVE LOGITS
     Ltd
    1.23
     Holdings
    1.06
     LLC
    1.05
     subsidiary
    0.99
     subsidiaries
    0.97
     Corp
    0.87
     LLP
    0.86
     headquartered
    0.84
     Inc
    0.84
     LTD
    0.82
    Activations Density 0.139%

    No Known Activations