INDEX

Explanations

substantive and descriptive language related to algorithms and inversion concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.54

 <<<<<<<<<<<<<<

-0.52

DebuggerStep

-0.48

tagext

-0.47

->___

-0.46

extAlignment

-0.45

 foon

-0.45

transQ

-0.45

chaffenheit

-0.44

 pleaſure

-0.44

POSITIVE LOGITS

 inver

0.62

Lähteet

0.58

 inverted

0.56

Tembelea

0.54

 WIRE

0.49

 ProtoMessage

0.49

WIRE

0.48

verted

0.47

ver

0.47

 inversion

0.46

Activations Density 1.974%

substantive and descriptive language related to algorithms and inversion concepts

No Comments

No Known Activations