INDEX

Explanations

instances of high-impact ideas or significant shifts in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

chafts

-0.41

ξα

-0.36

at

-0.36

God

-0.36

Per

-0.35

uber

-0.35

in

-0.35

dí

-0.35

BeginContext

-0.34

usp

-0.34

POSITIVE LOGITS

 itſelf

1.17

tagHelperRunner

1.07

 themſelves

1.05

Efq

1.04

 '\\;'

1.01

 Jefus

1.00

 whoſe

0.98

 myſelf

0.96

 himſelf

0.96

 Monfieur

0.95

Activations Density 0.198%

instances of high-impact ideas or significant shifts in context

No Comments

No Known Activations