INDEX

Explanations

variations of the prefix "fra" or terms related to "fractions."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

InputTagHelper

-0.68

entile

-0.61

ollectionView

-0.58

verwijspagina

-0.57

ագրություններ

-0.55

 برابوك

-0.55

intios

-0.55

ouac

-0.54

DispatchToProps

-0.53

قایناقلار

-0.52

POSITIVE LOGITS

Fra

0.76

Fra

0.71

fra

0.67

 GenerationType

0.65

fra

0.62

 Frag

0.57

quently

0.51

ContentAsync

0.50

 Fras

0.49

FRA

0.49

Activations Density 0.101%

variations of the prefix "fra" or terms related to "fractions."

No Comments

No Known Activations