INDEX

Explanations

phrases and terms related to bias and selectivity, especially within contexts of political and scientific discussions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 doInBackground

-0.69

 Paglinawan

-0.69

 "");

-0.68

mongoose

-0.67

 tartalomajánló

-0.65

İstinadlar

-0.64

'));

-0.61

 surla

-0.60

__':

-0.60

 Theſe

-0.59

POSITIVE LOGITS

 selective

0.94

selective

0.92

 biased

0.92

 selectivity

0.90

 bias

0.90

Selective

0.88

 Selective

0.82

 Bias

0.81

 selectively

0.79

 sele

0.78

Activations Density 0.781%

phrases and terms related to bias and selectivity, especially within contexts of political and scientific discussions

No Comments

No Known Activations