INDEX

Explanations

sections or pieces of text with structured data or programming language elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

RegistryLite

-0.94

 <=",

-0.87

انيف

-0.86

:✨

-0.86

MLLoader

-0.85

StructEnd

-0.84

SequentialGroup

-0.84

 EconPapers

-0.81

LookAnd

-0.79

 PeEnEo

-0.79

POSITIVE LOGITS

 purpoſe

0.72

 ſtate

0.69

 ſtre

0.68

 houſe

0.67

 pleaſure

0.67

 uſed

0.66

 ſen

0.65

 myſelf

0.64

 himſelf

0.62

 diſt

0.62

Activations Density 0.073%

sections or pieces of text with structured data or programming language elements

No Comments

No Known Activations