INDEX

Explanations

programming-related terms and templates

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

GRect

-0.53

RTCK

-0.49

uxxxx

-0.48

kfree

-0.47

withIdentifier

-0.46

entrant

-0.46

forKey

-0.45

okan

-0.45

tvguidetime

-0.45

ipedi

-0.44

POSITIVE LOGITS

StoryboardSegue

0.61

 propOrder

0.54

hyrchwyd

0.52

 newBuilder

0.51

 Ruling

0.50

PerformLayout

0.50

 bambina

0.48

UnknownFieldSet

0.47

 ContentValues

0.47

 juiz

0.47

Activations Density 0.800%

programming-related terms and templates

No Comments

No Known Activations