INDEX

Explanations

discussions and labels relating to biases in society or statistics

oai_token-act-pair · gemini-2.0-flash

terms related to non-heteronormative identities

np_token-act-pair-logits · gpt-4o-mini

LGBTQ+ identity

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uxxxx

-0.66

writeFieldEnd

-0.59

ChildIndex

-0.57

 Walkover

-0.55

 culte

-0.54

migrationBuilder

-0.54

 ويكيپيديا

-0.52

 maîtres

-0.52

 marrow

-0.51

skrä

-0.50

POSITIVE LOGITS

non

0.78

Non

0.71

bi

0.68

saraba

0.66

Non

0.66

pan

0.65

NON

0.64

 trans

0.62

non

0.62

Pan

0.61

Activations Density 3.237%

discussions and labels relating to biases in society or statistics

terms related to non-heteronormative identities

LGBTQ+ identity

No Comments

No Known Activations