INDEX

Explanations

references to study results and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unknownFields

-1.03

ValueStyle

-0.89

 '\\;'

-0.86

 lenker

-0.85

 pinulongan

-0.84

styleType

-0.83

 BoxDecoration

-0.83

 الرياضيه

-0.82

tagHelperRunner

-0.79

mybatisplus

-0.77

POSITIVE LOGITS

<eos>

0.89

↵↵

0.75

↵

0.59

↵↵↵

0.58

0.55

).

0.55

0.52

The

0.52

").

0.51

Le

0.51

Activations Density 0.682%

references to study results and findings

No Comments

No Known Activations