© 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. 14824
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to public relations (PR)

    oai_token-act-pair · gpt-3.5-turbo

    references to public relations (PR) entities or activities

    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
    lihood
    -0.82
     Presbyter
    -0.79
     Genesis
    -0.76
     Resurrection
    -0.76
    lings
    -0.70
     Runes
    -0.68
     Tale
    -0.67
    forth
    -0.67
     Mighty
    -0.65
    querque
    -0.65
    POSITIVE LOGITS
    INC
    1.12
    IME
    1.07
    ISM
    1.01
    INT
    0.99
    IZE
    0.99
    IOR
    0.96
    INTER
    0.95
    ODUCT
    0.95
    OPER
    0.94
    OF
    0.93
    Activations Density 0.006%

    No Known Activations