INDEX

Explanations

sections related to education and assessment information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<sup>

-0.50

href

-0.47

hu

-0.47

 distanciation

-0.47

-0.45

-0.44

hire

-0.43

忽

-0.42

nextLine

-0.42

POSITIVE LOGITS

 Monfieur

0.95

UnsafeEnabled

0.90

 myſelf

0.87

 themſelves

0.86

 itſelf

0.85

BibitemShut

0.85

 Jefus

0.85

 ―――――

0.84

^(@)

0.83

StructEnd

0.83

Activations Density 0.317%

sections related to education and assessment information

No Comments

No Known Activations