INDEX

Explanations

discussions around neutrality and bias in research

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 FetchType

-0.50

ChildScrollView

-0.49

AddTagHelper

-0.48

jednoc

-0.47

 Inscrivez

-0.46

 kirj

-0.46

Pcd

-0.45

ândia

-0.44

ætter

-0.43

strptime

-0.43

POSITIVE LOGITS

 bias

2.04

 biased

1.86

 Bias

1.71

 biases

1.69

bias

1.59

biased

1.56

Bias

1.53

biases

1.33

BIAS

1.30

 favoring

1.18

Activations Density 0.609%

discussions around neutrality and bias in research

No Comments

No Known Activations