INDEX

Explanations

occurrences of the word "in" in various contexts

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

for in range

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

transQ

-0.77

 betweenstory

-0.76

ConstraintMaker

-0.60

رشف

-0.60

thâu

-0.55

IntoConstraints

-0.53

󠁿

-0.53

 estekak

-0.53

℠

-0.52

UserScript

-0.52

POSITIVE LOGITS

 list

0.55

import

0.46

 items

0.44

 collection

0.42

 members

0.42

the

0.41

 listed

0.41

Cuánto

0.41

 range

0.41

Activations Density 0.005%

occurrences of the word "in" in various contexts

for in range

No Comments

No Known Activations