INDEX

Explanations

words related to job roles and positions

oai_token-act-pair · gpt-3.5-turbo

terms related to job roles and positions in the workforce

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

reb

-0.63

idan

-0.62

Prot

-0.60

Benz

-0.60

irus

-0.59

shield

-0.59

REAM

-0.59

Attempts

-0.59

 EDITION

-0.59

leaf

-0.58

POSITIVE LOGITS

hips

1.18

paces

1.17

hops

1.12

mith

1.01

pace

1.00

pring

0.99

hare

0.99

hip

0.97

uits

0.92

 roles

0.92

Activations Density 0.111%

words related to job roles and positions

terms related to job roles and positions in the workforce

No Comments

No Known Activations