INDEX

Explanations

questions or statements that challenge the validity or perception of facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

mybatisplus

-0.63

istoitu

-0.61

 itſelf

-0.58

 raiſ

-0.55

bootstrapcdn

-0.55

 myſelf

-0.53

AccessorTable

-0.52

pexpr

-0.49

 BoxDecoration

-0.48

 незавершена

-0.48

POSITIVE LOGITS

 conmigo

0.63

 realise

0.55

 vean

0.54

DropTable

0.54

Personendaten

0.54

 realize

0.54

DockStyle

0.53

ælp

0.53

boni

0.52

 AssemblyCulture

0.50

Activations Density 0.261%

questions or statements that challenge the validity or perception of facts

No Comments

No Known Activations