INDEX

Explanations

references to anecdotes or personal stories

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

Follows personal anecdotes or stories

np_acts-logits-general · gemini-2.0-flash

telling a story once

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

primarily

-0.55

 Hopefully

-0.54

 primarily

-0.53

Hopefully

-0.53

saraba

-0.50

ありがとうございます

-0.50

 Further

-0.49

 continuing

-0.47

Further

-0.47

 dals

-0.46

POSITIVE LOGITS

 once

2.51

once

2.15

Once

1.93

 Once

1.87

 ONCE

1.84

ONCE

1.74

 pernah

1.67

 kiedyś

1.52

 ooit

1.39

 einmal

1.38

Activations Density 0.422%

references to anecdotes or personal stories

Follows personal anecdotes or stories

telling a story once

No Comments

No Known Activations