INDEX

Explanations

keywords related to programming functions and methods

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

Mathematical or code-related symbols

np_acts-logits-general · gemini-2.0-flash

code snippets and technical references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

")"

-0.46

AndEndTag

-0.46

NAP

-0.45

ALO

-0.43

 chú

-0.41

terly

-0.40

हि

-0.40

')";

-0.40

Shy

-0.39

HIP

-0.39

POSITIVE LOGITS

UnsafeEnabled

1.09

WriteTagHelper

1.05

featureID

1.03

脚注の使い方

1.00

ագրություններ

0.96

GeoNames

0.95

 Baillargeon

0.94

 تكبرها

0.94

CloseOperation

0.93

AutoScaleMode

0.93

Activations Density 1.372%

keywords related to programming functions and methods

Mathematical or code-related symbols

code snippets and technical references

No Comments

No Known Activations