INDEX

Explanations

comparative phrases and measurements in scientific contexts

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

Allora

-0.52

 gekomen

-0.48

 earlier

-0.47

BeginContext

-0.47

 previously

-0.45

стер

-0.44

MLLoader

-0.44

Selanjutnya

-0.43

 that

-0.43

 later

-0.43

POSITIVE LOGITS

OGND

0.84

 gela

0.69

awaiter

0.67

protoimpl

0.66

 BoxFit

0.63

 كومونز

0.62

kloped

0.62

writeFieldEnd

0.61

setVerticalGroup

0.60

 chande

0.60

Activations Density 0.947%

comparative phrases and measurements in scientific contexts

No Comments

No Known Activations