INDEX

Explanations

interrogative pronouns, particularly "who," "what," and "where."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

findpost

-1.10

Portale

-0.93

 doubtnut

-0.86

 CURIAM

-0.84

 الحره

-0.83

CppMethod

-0.82

 surla

-0.81

 kasarigan

-0.81

"""

-0.78

 समीक्षक

-0.78

POSITIVE LOGITS

 whether

0.60

0.55

0.54

0.53

if

0.51

Whether

0.51

Whatever

0.49

 Whether

0.48

for

0.46

 whatever

0.46

Activations Density 0.310%

interrogative pronouns, particularly "who," "what," and "where."

No Comments

No Known Activations