INDEX

Explanations

clauses that express assertions or claims about a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

NameInMap

-0.73

िखित

-0.67

VES

-0.67

 Josephus

-0.66

 fufficient

-0.65

 Viter

-0.65

 Jacobi

-0.65

 talkin

-0.64

 Dior

-0.64

Mao

-0.64

POSITIVE LOGITS

 that

1.17

the

0.96

that

0.95

 there

0.94

assertThat

0.93

 bahwa

0.93

 bahawa

0.92

it

0.92

 they

0.89

 THAT

0.85

Activations Density 0.368%

clauses that express assertions or claims about a subject

No Comments

No Known Activations