INDEX

Explanations

references to personal experiences and interactions with others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Theſe

-0.87

aguya

-0.85

 Anſ

-0.84

 Suivez

-0.83

 purpoſe

-0.82

 Inscrivez

-0.82

 pleaf

-0.75

 Majefty

-0.74

 propof

-0.74

 Gabor

-0.74

POSITIVE LOGITS

parsedMessage

0.85

 ComVisible

0.74

SourceChecksum

0.63

 that

0.62

adpleegd

0.62

 although

0.61

esModule

0.60

RemoveField

0.58

mektedir

0.58

CppMethod

0.58

Activations Density 0.236%

references to personal experiences and interactions with others

No Comments

No Known Activations