INDEX

Explanations

terms related to the concept of absorption

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

 brady

-0.68

ẵn

-0.55

 дове

-0.54

 hiperten

-0.53

gadier

-0.52

 tội

-0.52

 candidat

-0.52

cardo

-0.51

 Field

-0.50

 Whitfield

-0.50

POSITIVE LOGITS

 absorbing

2.07

 absorb

2.04

 Absor

2.04

 absorbs

1.96

 absorbed

1.93

 absorption

1.89

 Absorption

1.83

Absor

1.82

 Absorb

1.80

absorbing

1.77

Activations Density 0.268%

terms related to the concept of absorption

No Comments

No Known Activations