INDEX

Explanations

references to sources or authorship

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

 itſelf

-1.28

 ―――――

-1.16

 ſind

-1.16

 myſelf

-1.13

 Anſ

-1.10

StoryboardSegue

-1.09

 ་་

-1.09

$_"

-1.07

ſelf

-1.06

'},

-1.05

POSITIVE LOGITS

1.87

1.24

：

0.98

:-

0.87

↵

0.86

.:

0.85

:[

0.81

:.

0.80

↵↵

0.78

::

0.76

Activations Density 0.439%

references to sources or authorship

No Comments

No Known Activations