INDEX

Explanations

patterns associated with various forms of messaging or information exchange

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

complexType

-0.48

umn

-0.45

Doy

-0.45

 coag

-0.44

<eos>

-0.44

 patriarch

-0.43

angelo

-0.43

 Amend

-0.43

↩

-0.42

variants

-0.41

POSITIVE LOGITS

__":

0.90

 متعلقه

0.90

 bezeichneter

0.78

ImageContext

0.78

 henvisninger

0.77

脚注の使い方

0.77

(!__

0.69

tagHelperRunner

0.68

Hochspringen

0.68

ThroughAttribute

0.67

Activations Density 0.026%

patterns associated with various forms of messaging or information exchange

No Comments

No Known Activations