INDEX

Explanations

phrases indicating time limitations or conditions surrounding events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.70

ſelf

-0.69

 ſmall

-0.69

 houſe

-0.68

 Jefus

-0.66

 ſta

-0.66

setImageBitmap

-0.66

 pleaſure

-0.65

ſelves

-0.65

 ſte

-0.65

POSITIVE LOGITS

 until

1.24

until

1.12

 till

1.05

 UNTIL

1.05

 Until

1.04

Until

1.04

til

0.91

 untill

0.90

 hasta

0.87

 μέχρι

0.87

Activations Density 0.273%

phrases indicating time limitations or conditions surrounding events

No Comments

No Known Activations