INDEX

Explanations

words related to professions or roles

oai_token-act-pair · gpt-3.5-turbo

words related to professions and roles

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

 guiActiveUn

-0.73

gol

-0.62

Obj

-0.61

DeL

-0.60

 COUR

-0.60

 defect

-0.59

 inev

-0.59

Tuc

-0.59

é¾įå

-0.58

 Belg

-0.58

POSITIVE LOGITS

ners

0.84

rina

0.78

ums

0.78

eper

0.77

ira

0.76

lla

0.75

urs

0.75

ft

0.74

aires

0.74

Activations Density 0.138%

words related to professions or roles

words related to professions and roles

No Comments

No Known Activations