INDEX

Explanations

conversational or questioning phrases indicating uncertainty or a request for clarification

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

Following "to"

np_acts-logits-general · gemini-2.0-flash

integrating and context

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

AutoScaleMode

-0.79

parsedMessage

-0.74

RegressionTest

-0.64

tonsoft

-0.64

 unknownFields

-0.62

 <=",

-0.62

 noqa

-0.61

ViewFeatures

-0.60

HasForeignKey

-0.60

########.

-0.60

POSITIVE LOGITS

Datuak

0.60

 fjer

0.51

Comes

0.48

Integrating

0.46

viato

0.46

 tilbake

0.45

IntegrationTest

0.44

breath

0.44

loro

0.44

BeginContext

0.44

Activations Density 0.038%

conversational or questioning phrases indicating uncertainty or a request for clarification

Following "to"

integrating and context

No Comments

No Known Activations