INDEX

Explanations

variations of the word "any."

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

Followed by possible continuations

np_acts-logits-general · gemini-2.0-flash

any followed by a word

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

stdc

-0.64

Griffin

-0.62

 Passat

-0.58

 Keats

-0.55

 cherchés

-0.55

stdafx

-0.54

slideUp

-0.53

 referrerpolicy

-0.53

scriptcase

-0.53

 Gorg

-0.53

POSITIVE LOGITS

any

1.06

Any

1.03

ANY

0.97

Any

0.97

any

0.91

ANY

0.91

antMatchers

0.89

body

0.82

glicher

0.80

rungsseite

0.77

Activations Density 0.117%

variations of the word "any."

Followed by possible continuations

any followed by a word

No Comments

No Known Activations