INDEX

Explanations

action verbs related to completion or execution

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "out."

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

antry

-0.78

avorite

-0.65

antine

-0.61

isma

-0.59

tyr

-0.57

ppy

-0.57

Missing

-0.56

kefeller

-0.56

EY

-0.56

Export

-0.55

POSITIVE LOGITS

wards

1.22

stretched

1.20

posts

1.13

fitted

1.10

casts

1.06

 loud

0.94

ta

0.91

bur

0.90

flows

0.87

smart

0.83

Activations Density 0.095%

action verbs related to completion or execution

occurrences of the word "out."

No Comments

No Known Activations