INDEX

Explanations

recommendations and suggestions related to media or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

JspWriter

-0.63

MemoryWarning

-0.57

 numerus

-0.57

 ArrayAdapter

-0.55

 valmis

-0.55

eraard

-0.54

UnusedPrivate

-0.54

 dibat

-0.53

MigrationBuilder

-0.51

 tarvit

-0.51

POSITIVE LOGITS

try

1.44

Try

1.28

Try

1.26

try

1.19

TRY

1.13

TRY

1.13

 попробовать

1.10

试试

1.08

 попробу

1.07

試試

1.05

Activations Density 0.175%

recommendations and suggestions related to media or experiences

No Comments

No Known Activations