INDEX

Explanations

recommendations and suggestions for actions to take

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

Imperative verbs following "you"

np_acts-logits-general · gemini-2.0-flash

you to do

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 avoit

-0.68

 amitié

-0.61

 obſ

-0.57

 waschen

-0.56

 négociations

-0.53

 quæ

-0.53

 étoit

-0.52

reordered

-0.51

isor

-0.51

 dibat

-0.51

POSITIVE LOGITS

 head

1.07

 grab

0.95

 headed

0.94

hop

0.89

 heading

0.85

hit

0.83

 HEAD

0.83

Head

0.83

pop

0.82

 jump

0.80

Activations Density 0.276%

recommendations and suggestions for actions to take

Imperative verbs following "you"

you to do

No Comments

No Known Activations