INDEX

Explanations

references to negative interpersonal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 autorytatywna

-0.44

BeginContext

-0.38

findpost

-0.37

ArrowToggle

-0.36

期刊论文

-0.34

beforeEach

-0.34

ísticas

-0.33

Huile

-0.32

MLLoader

-0.32

 always

-0.32

POSITIVE LOGITS

 perhaps

0.74

perhaps

0.68

 maybe

0.66

 probably

0.63

 Perhaps

0.62

Perhaps

0.62

 possibly

0.59

 Maybe

0.58

Probably

0.58

probably

0.57

Activations Density 0.846%

references to negative interpersonal experiences

No Comments

No Known Activations