INDEX

Explanations

words indicating relationships or commonalities between entities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-1.10

“

-0.88

'],'

-0.78

-0.69

 mena

-0.67

-0.65

dina

-0.63

taler

-0.63

']").

-0.63

alapa

-0.63

POSITIVE LOGITS

Efq

1.12

 itſelf

1.01

 Cæsar

1.00

quele

0.95

soever

0.92

ostante

0.92

withstanding

0.90

 auffi

0.90

 myſelf

0.89

Rptr

0.88

Activations Density 0.162%

words indicating relationships or commonalities between entities or actions

No Comments

No Known Activations