INDEX

Explanations

phrases and qualifiers indicating conditionality or evidence in complex scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 LoggerFactory

-0.70

}")]

-0.68

Datuak

-0.65

 Calvo

-0.65

CloseOperation

-0.65

JspWriter

-0.61

φάλ

-0.60

::~

-0.59

isSuccessful

-0.59

sandwich

-0.58

POSITIVE LOGITS

parsedMessage

0.58

 gynhyrchwyd

0.57

who

0.52

 magari

0.49

 الرياضيه

0.48

 interesado

0.47

 things

0.47

Who

0.46

 quién

0.46

 faptul

0.45

Activations Density 0.533%

phrases and qualifiers indicating conditionality or evidence in complex scenarios

No Comments

No Known Activations