INDEX

Explanations

mathematical functions and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 itſelf

-1.09

 ―――――

-0.96

 Anſ

-0.93

 myſelf

-0.91

 ་་

-0.90

 pleaſure

-0.90

ſy

-0.88

 Reſ

-0.85

 unſ

-0.85

 Inſ

-0.84

POSITIVE LOGITS

0.98

0.88

 resourceCulture

0.85

0.66

gården

0.65

niająca

0.65

et

0.64

eronau

0.62

encouragement

0.62

sampled

0.62

Activations Density 0.903%

mathematical functions and programming constructs

No Comments

No Known Activations