INDEX

Explanations

references to menu-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.68

-0.63

-0.61

in

-0.57

-0.56

-0.54

↵↵

-0.54

“

-0.53

-0.51

POSITIVE LOGITS

 pleaſure

1.33

AsUp

1.20

 Theſe

1.13

RectangleBorder

1.12

 myſelf

1.10

 themſelves

1.10

 houſe

1.09

 greateſt

1.08

 Jefus

1.05

 للمعارف

1.04

Activations Density 0.119%

references to menu-related concepts

No Comments

No Known Activations