INDEX

Explanations

words or roots related to specific dependencies or components in a software or programming context

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

letter u

np_max-act-logits · claude-3-7-sonnet-20250219 Triggered by @johnny

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

ValueStyle

-0.76

SharedCtor

-0.65

 complementa

-0.58

lines

-0.56

mos

-0.55

RenderAtEndOf

-0.53

twimg

-0.53

ammlung

-0.53

Threat

-0.52

ting

-0.52

POSITIVE LOGITS

uuuu

0.93

uuu

0.88

0.81

uuuuu

0.76

uu

0.72

COUVER

0.64

UUUU

0.64

du

0.63

0.57

UU

0.55

Activations Density 0.458%

words or roots related to specific dependencies or components in a software or programming context

letter u

No Comments

No Known Activations