INDEX

Explanations

items and numerical data in structured formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 estekak

-0.55

）。

-0.47

PhysRevD

-0.46

）.

-0.44

<eos>

-0.43

HtmlAttribute

-0.42

 autorytatywna

-0.41

</u>

-0.41

Ty

-0.40

Referanser

-0.40

POSITIVE LOGITS

 '\\;'

0.79

 propOrder

0.71

DebuggerStep

0.69

AutoScale

0.65

miyorum

0.64

يميديا

0.63

tvguidetime

0.63

 FetchType

0.62

WillAppear

0.62

 Taktlose

0.61

Activations Density 0.175%

items and numerical data in structured formats

No Comments

No Known Activations