INDEX

Explanations

explicit mentions of personal experiences and opinions

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

 DialogInterface

-0.51

сми

-0.46

findpost

-0.46

おお

-0.46

IsContent

-0.43

好在

-0.43

зин

-0.42

mybatisplus

-0.42

 للمعارف

-0.42

 كومونز

-0.42

POSITIVE LOGITS

 simply

3.49

 just

3.49

just

3.17

simply

3.11

 simplemente

3.03

 merely

2.87

 semplicemente

2.79

Just

2.76

 просто

2.73

Simply

2.72

Activations Density 1.009%

explicit mentions of personal experiences and opinions

No Comments

No Known Activations