© 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. 22575
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or impacts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate relationships or connections between ideas or phrases

    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
    DragonMagazine
    -0.82
    estern
    -0.80
    ãĥ¯ãĥ³
    -0.77
    lication
    -0.76
    wic
    -0.75
    osate
    -0.68
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.67
    livious
    -0.67
    abouts
    -0.66
    BLIC
    -0.66
    POSITIVE LOGITS
     jeopard
    1.07
     prevents
    1.06
     undermines
    1.05
     thereby
    1.02
     reduces
    1.01
     enhances
    1.00
     causing
    1.00
     detract
    0.99
     adversely
    0.97
     inhibits
    0.97
    Activations Density 0.391%

    No Known Activations