INDEX

Explanations

occurrences of the word "leads."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

die

-0.62

po

-0.56

wnątrz

-0.55

-0.53

ab

-0.53

اشی

-0.53

filepath

-0.53

款

-0.52

jante

-0.51

ob

-0.51

POSITIVE LOGITS

 itſelf

1.23

 Houſe

1.19

 pleaſure

1.06

 Reſ

1.05

ſelves

1.04

 Theſe

1.03

 houſe

1.03

ſelf

1.02

 Monfieur

1.01

 reaſon

1.00

Activations Density 0.075%

occurrences of the word "leads."

No Comments

No Known Activations