INDEX

Explanations

keywords related to health-related warnings and consequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.58

ans

-0.48

</strong>

-0.40

WindowConstants

-0.39

↵

-0.39

 modelAndView

-0.38

šlo

-0.37

viertel

-0.37

ta

-0.36

明

-0.36

POSITIVE LOGITS

CloseOperation

0.86

醐

0.86

 Wikimedijinoj

0.82

httphttps

0.81

évaluateur

0.79

WriteAttribute

0.78

 nakalista

0.75

EndTag

0.74

Diwedd

0.74

 itſelf

0.72

Activations Density 1.247%

keywords related to health-related warnings and consequences

No Comments

No Known Activations