INDEX

Explanations

HTML tags and formatting cues in the text

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

HTML heading tags of level 2 and 4

np_acts-logits-general · gemini-2.0-flash

mamie and momoyama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<strong>

-0.51

MockMvc

-0.48

igli

-0.47

-0.46

 human

-0.46

ho

-0.46

-0.45

<b>

-0.45

anthene

-0.45

-0.44

POSITIVE LOGITS

 }}"></

0.98

CloseOperation

0.96

 bezeichneter

0.90

."</

0.89

ScopeManager

0.84

MLLoader

0.80

.*")]

0.77

verwijspagina

0.75

ChildScrollView

0.75

^(@)

0.73

Activations Density 0.031%

HTML tags and formatting cues in the text

HTML heading tags of level 2 and 4

mamie and momoyama

No Comments

No Known Activations