INDEX

Explanations

phrases that indicate additional content or references to further reading

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

PyExc

-0.68

esModule

-0.66

Jegyzetek

-0.61

XmlAccessType

-0.59

Begriffsklä

-0.58

CppCodeGen

-0.58

 autorytatywna

-0.58

ulosa

-0.57

getStatusCode

-0.57

Hozzáférés

-0.56

POSITIVE LOGITS

 Paglinawan

0.69

 pleaſure

0.63

 unread

0.62

 reread

0.60

AutoSize

0.59

 gelesen

0.59

 readership

0.58

 nemico

0.58

เท้า

0.57

 financière

0.56

Activations Density 0.157%

phrases that indicate additional content or references to further reading

No Comments

No Known Activations