INDEX

Explanations

forms of the verb "to be."

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

Follows "is", "are", "was", or numbers

np_acts-logits-general · gemini-2.0-flash

existence phrases

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

AccessorTable

-0.91

 quæ

-0.86

 purpoſe

-0.86

 pleaſure

-0.80

 ſame

-0.80

AddTagHelper

-0.79

 Diſ

-0.79

 ſever

-0.79

 ſtand

-0.78

 fevere

-0.78

POSITIVE LOGITS

in

0.76

0.58

 when

0.56

 from

0.53

to

0.52

on

0.52

for

0.52

 sendiri

0.49

Parcelize

0.48

 disponibilités

0.48

Activations Density 0.137%

forms of the verb "to be."

Follows "is", "are", "was", or numbers

existence phrases

No Comments

No Known Activations