INDEX

Explanations

expressions indicating singular entities or concepts

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

"One" followed by a temporal unit

np_acts-logits-general · gemini-2.0-flash

“one” followed by a noun

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rungsseite

-0.72

AndEndTag

-0.61

adaptiveStyles

-0.59

EndInit

-0.58

 pleaſure

-0.56

endpush

-0.56

ArrowToggle

-0.55

ſu

-0.55

 Meksiku

-0.55

 ſche

-0.54

POSITIVE LOGITS

 كومونز

0.71

 single

0.63

kuuta

0.59

 liners

0.58

theless

0.57

}{*}{

0.55

single

0.54

 sürü

0.52

 liner

0.51

 Single

0.51

Activations Density 0.638%

expressions indicating singular entities or concepts

"One" followed by a temporal unit

“one” followed by a noun

No Comments

No Known Activations