INDEX

Explanations

punctuation marks that signify pauses or separations in text

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

conditional probability and outcomes

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

ſelves

-0.84

IVEREF

-0.82

tagHelperRunner

-0.72

setVerticalGroup

-0.72

Datuak

-0.72

ſelf

-0.71

ThroughAttribute

-0.70

Tembelea

-0.70

IUrlHelper

-0.69

 protoimpl

-0.69

POSITIVE LOGITS

ox

0.38

dan

0.37

 recommended

0.36

chi

0.35

lu

0.34

use

0.34

gang

0.33

Ma

0.32

cry

0.31

can

0.31

Activations Density 0.001%

punctuation marks that signify pauses or separations in text

conditional probability and outcomes

No Comments

No Known Activations