INDEX

Explanations

references to JSON formatting and its various characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

✨:

-0.88

SBATCH

-0.84

GrantedAuthority

-0.84

(&:

-0.83

$#

-0.83

InjectAttribute

-0.81

 myſelf

-0.81

awakeFromNib

-0.80

Efq

-0.79

initis

-0.78

POSITIVE LOGITS

 json

2.19

json

2.09

 JSON

1.89

Json

1.86

 Json

1.86

JSON

1.70

toJson

1.17

ToJson

1.13

getJSON

1.04

fromJson

1.00

Activations Density 0.062%

references to JSON formatting and its various characteristics

No Comments

No Known Activations