INDEX

Explanations

terms related to geometric shapes and designs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

!*\

-0.67

rawDesc

-0.60

endpush

-0.58

providedIn

-0.58

المكان

-0.56

 "..\..\

-0.55

bufio

-0.55

CDATA

-0.54

XtraBars

-0.53

 समीक्षक

-0.53

POSITIVE LOGITS

shaped

1.09

 shaped

1.07

 shape

1.02

 Shaped

0.93

shape

0.89

Shaped

0.87

 shapes

0.86

haped

0.85

 SHAPE

0.82

SHAPE

0.81

Activations Density 0.453%

terms related to geometric shapes and designs

No Comments

No Known Activations