INDEX

Explanations

instances of the word "this" and its variations

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

this followed by explanation

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

 IBOutlet

-0.48

 soap

-0.47

hyrchwyd

-0.47

LookAnd

-0.46

 parlour

-0.45

 Rotating

-0.45

 houſe

-0.45

 freezer

-0.45

lrrrr

-0.45

 haer

-0.43

POSITIVE LOGITS

AccessorTable

0.61

 spowod

0.52

 resulting

0.49

 means

0.47

 caused

0.45

 powod

0.45

 enables

0.44

 allows

0.44

 continúas

0.44

 wodurch

0.43

Activations Density 0.130%

instances of the word "this" and its variations

this followed by explanation

No Comments

No Known Activations