INDEX

Explanations

HTML closing tags

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

tvguidetime

-1.09

ніципа

-0.92

 disambiguazione

-0.91

Източници

-0.90

 يتيمه

-0.89

WithIOException

-0.88

WriteTagHelper

-0.87

 Monfieur

-0.87

Rüyada

-0.85

 ainfi

-0.84

POSITIVE LOGITS

and

0.56

0.55

0.53

0.51

0.49

0.48

xiu

0.47

an

0.47

Activations Density 0.038%

HTML closing tags

No Comments

No Known Activations