INDEX

Explanations

references to frames in various contexts

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

frames, interpolation and frame rates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 kaarangay

-0.43

transQ

-0.40

expandindo

-0.39

 strconv

-0.37

 GenerationType

-0.36

 colgantes

-0.36

แก่

-0.34

 teorías

-0.34

HomeAsUpEnabled

-0.33

AnchorTagHelper

-0.32

POSITIVE LOGITS

 frame

1.78

 Frame

1.66

 frames

1.64

 Frames

1.56

Frame

1.52

 FRAME

1.40

frames

1.40

frame

1.38

Frames

1.30

FRAME

1.25

Activations Density 0.004%

references to frames in various contexts

frames, interpolation and frame rates

No Comments

No Known Activations