INDEX

Explanations

terms related to stereoscopic imagery and its applications

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

stereopairs and stereoscopic vision

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 COVID

-0.60

 Covid

-0.60

Nox

-0.57

 CommonModule

-0.56

Quinn

-0.56

 Flux

-0.56

Fig

-0.56

 ApiClient

-0.56

ICH

-0.56

findpost

-0.56

POSITIVE LOGITS

EREO

0.58

 Ster

0.56

stereotype

0.54

 Stern

0.54

 stere

0.54

stere

0.53

 Stearns

0.53

Ster

0.52

Stereo

0.51

Stern

0.50

Activations Density 0.017%

terms related to stereoscopic imagery and its applications

stereopairs and stereoscopic vision

No Comments

No Known Activations