INDEX

Explanations

references to time-related terms, particularly involving the word "last."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 defaultstate

-0.63

 esternos

-0.62

 eventdata

-0.60

 nahilalakip

-0.59

 позже

-0.59

 pozdě

-0.59

\{\\

-0.58

InjectAttribute

-0.57

ViewFeatures

-0.56

 manhã

-0.55

POSITIVE LOGITS

 resort

0.93

 minute

0.85

resort

0.81

minute

0.79

 Resort

0.78

 getLast

0.76

 straw

0.76

ingly

0.73

Resort

0.73

est

0.71

Activations Density 0.088%

references to time-related terms, particularly involving the word "last."

No Comments

No Known Activations