INDEX

Explanations

expressions of hope and enthusiasm for future events or participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

帖最后由

-0.64

covite

-0.51

 vPvB

-0.51

RegressionTest

-0.50

saraba

-0.49

ệnh

-0.49

isition

-0.48

期刊论文

-0.48

InSection

-0.48

Clik

-0.47

POSITIVE LOGITS

 look

1.81

 Look

1.54

look

1.53

Look

1.46

 looking

1.38

 LOOK

1.30

 Looking

1.20

looking

1.16

LOOK

1.14

Looking

1.12

Activations Density 0.267%

expressions of hope and enthusiasm for future events or participation

No Comments

No Known Activations