INDEX

Explanations

HTML closing tags

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

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

adpleegd

-0.74

رشف

-0.69

 "..\..\..\

-0.65

 通販

-0.65

LookAnd

-0.63

__);

-0.63

TProtocol

-0.63

 ComVisible

-0.62

IntoConstraints

-0.61

XMLSchema

-0.59

POSITIVE LOGITS

mi

0.65

Mip

0.59

posure

0.52

Mi

0.50

CodeAnalysis

0.49

 miRNAs

0.47

ми

0.46

IORITY

0.46

ränk

0.46

minor

0.45

Activations Density 0.035%

HTML closing tags

No Comments

No Known Activations