INDEX

Explanations

references to specific locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

zös

-0.52

rativa

-0.48

uxxxx

-0.47

 maska

-0.47

skosten

-0.47

 lenker

-0.45

 CNRS

-0.45

aarrggbb

-0.45

enoord

-0.45

athione

-0.43

POSITIVE LOGITS

 branch

1.12

 Branch

0.98

 location

0.92

branch

0.89

 locatie

0.89

 BRANCH

0.88

 Standort

0.84

Branch

0.82

 branches

0.81

 chapter

0.80

Activations Density 0.208%

references to specific locations and organizations

No Comments

No Known Activations