INDEX

Explanations

phrases indicating time references and previous occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

]")]

-0.56

 parteci

-0.54

ніципалі

-0.54

abestanden

-0.52

 habet

-0.52

 Dink

-0.51

DECREF

-0.51

 springfox

-0.51

addPreferredGap

-0.50

Ārējās

-0.50

POSITIVE LOGITS

 previous

0.85

ago

0.83

 PREVIOUS

0.75

Previous

0.73

 Previous

0.71

previous

0.71

Previously

0.70

PREVIOUS

0.70

 pasada

0.68

 previously

0.67

Activations Density 0.343%

phrases indicating time references and previous occurrences

No Comments

No Known Activations