INDEX

Explanations

terms related to accumulation and buildup processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

]--;

-0.58

//

-0.58

gill

-0.53

ardless

-0.52

QMetaType

-0.50

AutoresizingMask

-0.50

 tocado

-0.50

XmlAccessorType

-0.49

рована

-0.49

orce

-0.48

POSITIVE LOGITS

 accumulation

2.41

 accumulate

2.33

 accumulated

2.31

 accumulates

2.26

 accumulating

2.19

 Accumulation

2.13

 accum

2.13

 Accum

2.09

accum

2.07

Accum

2.06

Activations Density 0.410%

terms related to accumulation and buildup processes

No Comments

No Known Activations