INDEX

Explanations

terms related to showing evidence or making a case

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

bootstrapcdn

-0.78

slidesPer

-0.70

iseite

-0.70

 препратки

-0.70

Kirch

-0.70

 pinta

-0.69

aguya

-0.68

Lik

-0.68

useNewUrlParser

-0.68

 Aiken

-0.67

POSITIVE LOGITS

 demonstrators

1.35

 demonstrations

1.30

 demonstration

1.24

 Demonstration

1.16

Demonstration

1.16

 demonstrating

1.14

 demonstr

1.12

 Demonstr

1.12

 demos

1.12

 demonstrated

1.10

Activations Density 0.104%

terms related to showing evidence or making a case

No Comments

No Known Activations