INDEX

Explanations

technical specifications related to character encoding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 estimés

-0.75

OptionsMenu

-0.74

 kasarigan

-0.72

 lenker

-0.72

principalColumn

-0.71

 onCancelled

-0.71

 Alamos

-0.70

 propOrder

-0.70

 &___

-0.69

expandindo

-0.68

POSITIVE LOGITS

utf

3.51

UTF

2.56

utf

2.52

UTF

2.12

Utf

1.79

Utf

1.26

 charset

1.11

charset

1.02

Encoding

0.68

UTC

0.68

Activations Density 0.047%

technical specifications related to character encoding

No Comments

No Known Activations