INDEX

Explanations

numerical data and size specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 nakalista

-0.84

MessageOf

-0.82

Попис

-0.81

 الاطلاع

-0.71

 consultato

-0.68

 '\\;'

-0.66

RegistryLite

-0.63

 mohair

-0.62

 désolés

-0.62

msgTypes

-0.62

POSITIVE LOGITS

½

0.71

½

0.70

 Half

0.64

half

0.61

Half

0.60

 HALF

0.58

 half

0.56

Климат

0.56

️

0.55

HALF

0.55

Activations Density 0.300%

numerical data and size specifications

No Comments

No Known Activations