© 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. 9-RES-JB
    11. 4769
    Prev
    Next
    INDEX
    Explanations

    words related to successful outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "successful" and its variations, indicating positive outcomes or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alon
    -0.69
    pick
    -0.65
    thirst
    -0.65
    oline
    -0.65
    olyn
    -0.64
    facts
    -0.63
    Natural
    -0.63
    pler
    -0.62
    anguage
    -0.62
    ype
    -0.62
    POSITIVE LOGITS
     completion
    1.07
     bidder
    0.97
     integration
    0.85
     navig
    0.80
     applicant
    0.79
     prosecution
    0.77
     outreach
    0.72
     prosecutions
    0.72
     enterprises
    0.70
     Kickstarter
    0.69
    Activations Density 0.033%

    No Known Activations