INDEX

Explanations

phrases related to recommendations and suggestions for trying out various options

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

-0.73

__(/*!

-0.65

+#+#

-0.63

kháu

-0.57

 NavController

-0.55

 Exactos

-0.55

 transfieras

-0.55

forChild

-0.53

afficheront

-0.51

istoitu

-0.51

POSITIVE LOGITS

try

3.44

try

3.19

 tries

3.04

Try

2.96

Try

2.89

 tried

2.88

 trying

2.81

TRY

2.69

trying

2.51

 Trying

2.51

Activations Density 0.715%

phrases related to recommendations and suggestions for trying out various options

No Comments

No Known Activations