INDEX

Explanations

date-related information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Amicalement

-0.84

 EconPapers

-0.79

 Guel

-0.75

 unknownFields

-0.75

profiler

-0.75

findpost

-0.74

 Foote

-0.74

DockStyle

-0.72

 propOrder

-0.72

avoit

-0.71

POSITIVE LOGITS

DECEMBER

1.22

 Christmas

1.17

 December

1.13

Christmas

1.08

 DECEMBER

1.06

 CHRISTMAS

1.06

 Decker

1.05

December

1.05

DEC

1.00

 christmas

0.99

Activations Density 0.073%

date-related information

No Comments

No Known Activations