INDEX

Explanations

elements related to processes and changes in life experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.65

Begriffsklä

-0.56

thinkable

-0.56

Filmografie

-0.53

 EconPapers

-0.51

withIdentifier

-0.51

 незавершена

-0.49

Ape

-0.49

 TestBed

-0.48

 الحره

-0.48

POSITIVE LOGITS

 dabei

1.53

 daarbij

1.40

 meanwhile

1.28

 process

1.21

 meantime

1.19

 incidentally

1.11

 Dabei

1.11

顺便

1.09

Dabei

1.07

process

1.04

Activations Density 0.229%

elements related to processes and changes in life experiences

No Comments

No Known Activations