INDEX

Explanations

text structured as news articles or formal reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 even

-0.48

-0.46

it

-0.45

 zelfs

-0.44

Even

-0.44

↵↵

-0.44

 addirittura

-0.43

tamanya

-0.43

POSITIVE LOGITS

 originally

0.83

Hentet

0.81

Efq

0.78

ricle

0.73

originally

0.72

IContainer

0.72

GEBURTSDATUM

0.71

ViewFeatures

0.70

Originally

0.70

 Originally

0.70

Activations Density 0.300%

text structured as news articles or formal reports

No Comments

No Known Activations