INDEX

Explanations

technical terms related to coding or system errors

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

Numbers followed or preceded by colons or other number-related tokens

np_acts-logits-general · gemini-2.0-flash

rectangle(( or concluded that

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

众

-0.50

 Cole

-0.48

mtable

-0.47

RuleContext

-0.46

ledo

-0.46

可怜

-0.46



-0.45

 Савезне

-0.45

 nome

-0.45

tro

-0.44

POSITIVE LOGITS

tvguidetime

0.94

rrggbb

0.86

InstanceState

0.72

ConstraintMaker

0.70

 CURIAM

0.66

ViewInit

0.62

ressee

0.61

 itſelf

0.61

rubber

0.59

ształ

0.58

Activations Density 0.264%

technical terms related to coding or system errors

Numbers followed or preceded by colons or other number-related tokens

rectangle(( or concluded that

No Comments

No Known Activations