INDEX

Explanations

references to internal systems or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 queſta

-0.69

WaitGroup

-0.68

 avoient

-0.67

 müſſen

-0.67

 étoient

-0.65

BufferException

-0.64

出版年

-0.63

providedIn

-0.63

ésult

-0.63

///</

-0.63

POSITIVE LOGITS

 internal

1.24

 inside

1.21

Internal

1.17

 Internal

1.14

Inside

1.14

internal

1.13

inside

1.09

 Inside

1.09

 inner

1.02

INTERNAL

1.02

Activations Density 0.134%

references to internal systems or structures

No Comments

No Known Activations