INDEX

Explanations

terms related to synergistic and additive effects in scientific contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autant

-0.49

abetes

-0.47

Replacement

-0.44

官

-0.44

 Lucas

-0.43

ueuse

-0.43

sé

-0.43

 lenger

-0.42

galkan

-0.42

Ậ

-0.42

POSITIVE LOGITS

 synerg

1.01

BufferException

0.96

 synergistic

0.96

 synergy

0.93

 syner

0.88

 Synergy

0.87

 Syner

0.81

يكب

0.75

 Pote

0.75

 fathoms

0.74

Activations Density 0.005%

terms related to synergistic and additive effects in scientific contexts

No Comments

No Known Activations

terms related to synergistic and additive effects in scientific contexts

No Comments

No Known Activations