INDEX

Explanations

programming and coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Referencie

-0.48

Re

-0.47

StoryboardSegue

-0.46

Bar

-0.46

 <<<<<<<<<<<<<<

-0.45

ValueStyle

-0.44

pro

-0.44

AutoScale

-0.44

BASEPATH

-0.43

POSITIVE LOGITS

^(@)

0.90

ſelf

0.89

 auffi

0.87

 betweenstory

0.84

 raiſ

0.79

 uſed

0.78

EndGlobalSection

0.78

 pleaſure

0.77

 poffe

0.76

 faſt

0.75

Activations Density 0.925%

programming and coding structures

No Comments

No Known Activations