INDEX

Explanations

references to transformation or improvement in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 houſe

-0.70

 myſelf

-0.67

 pleaſure

-0.62

Efq

-0.58

 fhew

-0.58

 enfans

-0.57

 itſelf

-0.56

Eſ

-0.55

ſelves

-0.54

 Monfieur

-0.53

POSITIVE LOGITS

migrationBuilder

0.64

ⓧ

0.62

LookAnd

0.58

 становника

0.57

interopRequire

0.55

したのが

0.53

 backward

0.52

LEncoder

0.52

ftagPool

0.51

 steroids

0.51

Activations Density 0.382%

references to transformation or improvement in various contexts

No Comments

No Known Activations