INDEX

Explanations

mentions of specific entities or people

oai_token-act-pair · gpt-3.5-turbo

instances of the letter "A" at the beginning of phrases or sentences

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

 apes

-0.64

 stripes

-0.63

 appointments

-0.63

 disabilities

-0.63

 rebounds

-0.62

 noses

-0.62

 unconscious

-0.62

 lies

-0.61

oids

-0.61

 cylinders

-0.60

POSITIVE LOGITS

chieve

1.45

ircraft

1.40

uckland

1.38

gency

1.34

ctions

1.27

ctors

1.26

usterity

1.24

erial

1.24

UTH

1.24

ffect

1.21

Activations Density 0.078%

mentions of specific entities or people

instances of the letter "A" at the beginning of phrases or sentences

No Comments

No Known Activations