INDEX

Explanations

coding syntax related to programming functions and annotations, particularly in frameworks or libraries

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

<eos>

-0.53

The

-0.51

-0.48

ま

-0.42

 Although

-0.42

-0.41

-0.39

-0.38

iste

-0.36

POSITIVE LOGITS

 Houſe

1.12

تقاوى

1.09

 myſelf

1.07

 pleaſure

1.06

Efq

1.05

webElementXpaths

1.04

UnknownFieldSet

1.04

 houſe

1.01

 purpoſe

1.00

 InputDecoration

0.99

Activations Density 0.748%

coding syntax related to programming functions and annotations, particularly in frameworks or libraries

No Comments

No Known Activations