INDEX

Explanations

terms related to wrapping or enclosure in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

kloped

-0.67

OGND

-0.65

دانشنامهٔ

-0.63

TintMode

-0.63

 PLWABN

-0.59

gameserver

-0.59

 pegs

-0.59

!=-

-0.58

rąg

-0.58

ThroughAttribute

-0.56

POSITIVE LOGITS

 wrapping

0.69

 wrap

0.66

Wrapping

0.65

 wrapped

0.64

 wraps

0.64

 Wrapping

0.64

wrap

0.64

 Wrap

0.61

Wrap

0.57

 devi

0.55

Activations Density 1.827%

terms related to wrapping or enclosure in various contexts

No Comments

No Known Activations