© 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. 1-RES-JB
    11. 24164
    Prev
    Next
    INDEX
    Explanations

    terms related to significant consequences or aftermath, potentially with a focus on negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consequences or aftermath, especially in environmental or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aky
    -1.08
    pir
    -0.88
    rique
    -0.85
    licks
    -0.84
    liam
    -0.82
    umption
    -0.81
    uana
    -0.79
    cer
    -0.78
    haps
    -0.78
    cius
    -0.77
    POSITIVE LOGITS
     fallout
    1.76
     ripple
    0.94
     repercussions
    0.88
    romeda
    0.85
     DRAG
    0.84
    SourceFile
    0.80
    DragonMagazine
    0.80
     spill
    0.79
     aftermath
    0.79
     bombshell
    0.79
    Activations Density 0.013%

    No Known Activations