INDEX

Explanations

comparative phrases or constructs related to personal experiences and emotions

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

FieldOffsetTable

-0.65

rungsseite

-0.65

 EconPapers

-0.63

IntoConstraints

-0.61

mergeFrom

-0.59

 queſta

-0.59

 témoig

-0.57

Autoritní

-0.56

$_['

-0.56

 ویکی‌پدیای

-0.56

POSITIVE LOGITS

 подоб

0.59

 like

0.59

 such

0.50

这类

0.50

こういう

0.50

 solcher

0.49

 solche

0.47

这样的

0.47

 solchen

0.46

 مثل

0.44

Activations Density 0.314%

comparative phrases or constructs related to personal experiences and emotions

No Comments

No Known Activations