INDEX

Explanations

references to requirements or necessary actions and their implications in the context of a process or study

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

 ་་

-1.16

etheless

-1.13

 ―――――

-1.04

ſelves

-1.03

$_"

-1.02

 photolibrary

-0.98

 itſelf

-0.96

 doubtnut

-0.96

ressee

-0.94

(\<

-0.93

POSITIVE LOGITS

<eos>

1.13

↵↵

1.08

...

0.98

0.92

↵

0.91

↵↵↵

0.91

..

0.87

0.85

....

0.83

Activations Density 0.883%

references to requirements or necessary actions and their implications in the context of a process or study

No Comments

No Known Activations