INDEX

Explanations

references to in-person interactions and physical presence in conversations or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 réglable

-0.53

 histoires

-0.49

gyz

-0.49

 Vikipedi

-0.47

########.

-0.46

tembro

-0.45

 particulières

-0.45

isNameExpr

-0.45

 silicona

-0.43

jestel

-0.43

POSITIVE LOGITS

 physical

1.13

 physically

1.10

physical

0.97

 Physically

0.93

Physical

0.92

 Physical

0.92

 PHYSICAL

0.90

PHYSICAL

0.88

 presencial

0.86

 fysis

0.86

Activations Density 0.366%

references to in-person interactions and physical presence in conversations or processes

No Comments

No Known Activations