INDEX

Explanations

references to API documentation and versioning

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

ὖ

-0.77

Efq

-0.74

 Shakspeare

-0.67

IVEREF

-0.66

IUrlHelper

-0.63

 Pila

-0.63

 Pyrr

-0.62

 itſelf

-0.62

 dAtA

-0.62

 Signalez

-0.61

POSITIVE LOGITS

wikidata

0.57

 abgerufen

0.54

 then

0.54

 ويكيميديا

0.53

 Wicidata

0.52

 beaux

0.51

then

0.51

…

0.50

ValueStyle

0.50

Activations Density 0.270%

references to API documentation and versioning

No Comments

No Known Activations