INDEX

Explanations

phrases indicating social interactions or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AccessorTable

-0.71

 ModelExpression

-0.70

rativa

-0.68

 كمان

-0.61

InjectAttribute

-0.61

initComponents

-0.60

RetentionPolicy

-0.59

 MainAxisSize

-0.58

manteau

-0.58

WebElementEntity

-0.57

POSITIVE LOGITS

MethodManager

0.51

 ComVisible

0.51

 urbanos

0.49

شهاد

0.48

 سكانية

0.47

boutin

0.45

こち

0.45

 estekak

0.44

ExtendWith

0.43

iterranée

0.43

Activations Density 0.733%

phrases indicating social interactions or relationships

No Comments

No Known Activations