INDEX

Explanations

terms related to suffering and victimhood

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Források

-0.63

onViewCreated

-0.63

Pru

-0.62

PhysRev

-0.61

 myſelf

-0.57

 Secund

-0.56

existsSync

-0.54

PhysRevLett

-0.53

Mont

-0.53

γε

-0.52

POSITIVE LOGITS

 suffered

0.92

 suffer

0.87

 suffers

0.80

 recevoir

0.80

 sofrer

0.79

 sufrir

0.79

 undergone

0.79

 receives

0.76

 undergoes

0.76

 undergo

0.75

Activations Density 0.325%

terms related to suffering and victimhood

No Comments

No Known Activations