INDEX

Explanations

terms related to technical specifications and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

AsUp

-0.48

-0.44

 form

-0.43

ffron

-0.42

 player

-0.41

ือน

-0.40

臘

-0.40

ступа

-0.40

 everyone

-0.40

 everybody

-0.40

POSITIVE LOGITS

\{\\

1.40

tvguidetime

1.37

 للاسماء

1.30

BeginContext

1.24

 nakalista

1.12

</thead>

1.11

 initComponents

1.10

tagHelperRunner

1.07

 CreateTagHelper

1.04

 متعلقه

1.01

Activations Density 0.002%

terms related to technical specifications and documentation

No Comments

No Known Activations