INDEX

Explanations

functions and method calls related to document manipulation and UI elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.77

ſelf

-0.73

 ་་

-0.66

 iſt

-0.66

 ſal

-0.65

basicConfig

-0.64

 cherchés

-0.64

 ſche

-0.64

 Reſ

-0.64

tagHelperRunner

-0.64

POSITIVE LOGITS

appendChild

1.56

LikeLike

1.00

addSubview

0.88

 addSubview

0.75

thenReturn

0.74

removeChild

0.64

/-/

0.59

LikeLiked

0.56

dAtA

0.55

anyu

0.54

Activations Density 0.024%

functions and method calls related to document manipulation and UI elements

No Comments

No Known Activations