INDEX

Explanations

occurrences of the word "particular" and high-frequency words that suggest a focus or measurement

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

particular, point, mean

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

ⓧ

-0.64

terday

-0.63

 useAppContext

-0.60

toHaveBeenCalled

-0.59

ſelves

-0.59

 myſelf

-0.59

tanleria

-0.58

CodeAttribute

-0.57

medriver

-0.57

UserScript

-0.56

POSITIVE LOGITS

0.38

).

0.38

CrossRef

0.38

),

0.38

0.37

.)

0.36

 contenus

0.36

0.34

Activations Density 0.007%

occurrences of the word "particular" and high-frequency words that suggest a focus or measurement

particular, point, mean

No Comments

No Known Activations