INDEX

Explanations

conditional statements and examples in arguments or discussions

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

parsedMessage

-1.00

-0.94

tvguidetime

-0.92

 שוליים

-0.85

 CanadaChoose

-0.84

!*\

-0.83

Vidite

-0.83

Бахар

-0.82

fillType

-0.80

saraba

-0.79

POSITIVE LOGITS

 totiž

0.66

 namelijk

0.59

 infatti

0.58

 nämlich

0.54

0.53

 bowiem

0.50

0.49

 nemlig

0.47

had

0.47

).

0.46

Activations Density 0.767%

conditional statements and examples in arguments or discussions

No Comments

No Known Activations