INDEX

Explanations

references to notable web documentation or sources, particularly related to technical subjects

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

testify

-0.62

Obrázky

-0.61

ropriate

-0.58

 везе

-0.58

 transférez

-0.57

ulaski

-0.57

 يتيمه

-0.56

rials

-0.56

IsInitialized

-0.56

duled

-0.55

POSITIVE LOGITS

Morfologia

0.61

xmlns

0.59

Descripció

0.57

 resourceCulture

0.56

 RequestMethod

0.55

ungsbedingungen

0.55

헌

0.54

UniformLocation

0.52

stepper

0.50

HasAnnotation

0.49

Activations Density 0.039%

references to notable web documentation or sources, particularly related to technical subjects

No Comments

No Known Activations