INDEX

Explanations

female names

oai_token-act-pair · gpt-3.5-turbo

names of women and female spokespersons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.74

ints

-0.70

 sidx

-0.68

ypes

-0.67

iuses

-0.66

istar

-0.63

 surv

-0.62

arak

-0.62

PDATE

-0.62

Ñģ

-0.61

POSITIVE LOGITS

 Anne

1.21

 Louise

1.16

 Lynn

1.14

Anne

1.12

Ann

1.11

 Marie

1.10

Mae

1.10

 DeVos

1.09

 herself

1.07

 Jane

1.02

Activations Density 0.114%

female names

names of women and female spokespersons

No Comments

No Known Activations