INDEX

Explanations

conjunctions and relative pronouns that indicate relationships between clauses or phrases

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

"that" followed by a verb

np_acts-logits-general · gemini-2.0-flash

relative pronoun clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ion

-0.55

 snowing

-0.54

ual

-0.50

ly

-0.50

ed

-0.50

Chosen

-0.50

 elaboration

-0.49

est

-0.48

Nef

-0.48

ize

-0.47

POSITIVE LOGITS

can

1.05

is

1.03

 could

0.95

has

0.91

 will

0.88

 would

0.83

 might

0.81

tvguidetime

0.81

may

0.80

MENAFN

0.80

Activations Density 0.370%

conjunctions and relative pronouns that indicate relationships between clauses or phrases

"that" followed by a verb

relative pronoun clauses

No Comments

No Known Activations