INDEX

Explanations

percentages and statistical data

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

hawar

-0.72

LAM

-0.70

fstream

-0.70

;"></

-0.70

····

-0.70

 objectAtIndex

-0.68

na

-0.68

 Eisen

-0.67

 Lang

-0.67

ity

-0.65

POSITIVE LOGITS

\%$

1.43

1.31

\%

1.17

 percent

1.13

\%

1.12

 \%}$

1.11

%+

1.06

percent

1.06

/%

1.03

Activations Density 0.168%

percentages and statistical data

No Comments

No Known Activations