INDEX

Explanations

specific names, terms, and identifiers related to a range of topics including locations, organizations, and actions

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

AnimationsModule

-0.62

CppCodeGen

-0.58

bootstrapcdn

-0.57

photobucket

-0.57

ума

-0.56

:]

-0.49

用心

-0.48

CppMethod

-0.48

</h5>

-0.48

POSITIVE LOGITS

 myſelf

0.88

 Theſe

0.85

 Reſ

0.83

 Monfieur

0.82

 purpoſe

0.79

 leaſt

0.79

 reaſon

0.79

 Anſ

0.77

 houſe

0.77

Efq

0.77

Activations Density 3.315%

specific names, terms, and identifiers related to a range of topics including locations, organizations, and actions

No Comments

No Known Activations