INDEX

Explanations

terms related to biological and chemical systems

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

appearing before "group", "item", or "dataset"

np_acts-logits-general · gemini-2.0-flash

scientific and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 kasarigan

-0.93

 autorytatywna

-0.90

 مرئيه

-0.88

Geplaatst

-0.85

WriteTagHelper

-0.84

adaptiveStyles

-0.82

 nakalista

-0.82

NameInMap

-0.81

 Signalez

-0.80

 pinulongan

-0.80

POSITIVE LOGITS

 which

0.47

0.44

 also

0.44

 that

0.42

is

0.41

 with

0.41

↵↵

0.40

as

0.40

 will

0.40

Activations Density 0.406%

terms related to biological and chemical systems

appearing before "group", "item", or "dataset"

scientific and technical terms

No Comments

No Known Activations