INDEX

Explanations

patterns of repetition and emphasis in language

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

 oprot

-0.76

 defire

-0.75

 raiſ

-0.74

enterOuterAlt

-0.74

 PyLong

-0.73

 pleaſure

-0.73

 pinulongan

-0.72

 ſta

-0.72

 juſ

-0.71

 ſind

-0.70

POSITIVE LOGITS

 ganzen

0.55

 egentligen

0.47

 těch

0.45

 this

0.45

 those

0.44

 these

0.44

ieteur

0.43

 valt

0.42

 ihop

0.41

 aquela

0.40

Activations Density 0.085%

patterns of repetition and emphasis in language

No Comments

No Known Activations