INDEX

Explanations

questions or inquiries about information or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.77

StructEnd

-0.76

تقاوى

-0.74

SharedCtor

-0.73

 Paglinawan

-0.70

 ComVisible

-0.66

 Roskov

-0.66

 protoimpl

-0.66

 AssemblyCulture

-0.65

BackStack

-0.65

POSITIVE LOGITS

are

0.86

do

0.83

 role

0.76

 exactly

0.76

if

0.75

 else

0.73

 about

0.71

 kind

0.71

 kinds

0.69

 exatamente

0.68

Activations Density 0.202%

questions or inquiries about information or clarification

No Comments

No Known Activations