INDEX

Explanations

relationships involving legal or evaluative phrases and contexts

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

Referring expressions ("this", "that", "same")

np_acts-logits-general · gemini-2.0-flash

in a specific way or 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

tagHelperRunner

-0.92

CompleteListener

-0.78

日在

-0.75

 &___

-0.74

SourceChecksum

-0.73

ANTLR

-0.73

enumi

-0.71

InvalidProtocol

-0.71

AxisAlignment

-0.70

 الحره

-0.69

POSITIVE LOGITS

 context

1.00

 guise

0.93

 contexts

0.92

 וב

0.84

 vicinity

0.81

 manner

0.80

 hurry

0.77

 midst

0.77

context

0.75

 respects

0.74

Activations Density 1.448%

relationships involving legal or evaluative phrases and contexts

Referring expressions ("this", "that", "same")

in a specific way or context

No Comments

No Known Activations