INDEX

Explanations

adjectives describing attributes or skills

oai_token-act-pair · gpt-3.5-turbo

terms related to personal attributes and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

edIn

-0.76

adow

-0.73

Release

-0.65

bda

-0.62

EE

-0.62

outube

-0.58

AY

-0.58

æī

-0.57

vae

-0.57

 Release

-0.56

POSITIVE LOGITS

 necessary

1.27

liest

1.19

 requisite

1.14

 needed

1.13

iest

1.03

needed

0.99

 required

0.99

same

0.97

necessary

0.91

 desired

0.91

Activations Density 0.340%

adjectives describing attributes or skills

terms related to personal attributes and qualifications

No Comments

No Known Activations