INDEX

Explanations

words related to movement or action

oai_token-act-pair · gpt-3.5-turbo

the letter 'j' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Illum

-0.68

ãĥ´ãĤ¡

-0.66

 Metall

-0.65

 compe

-0.62

doors

-0.62

 Primal

-0.61

IUM

-0.60

 Fargo

-0.60

 Norn

-0.60

 Lauder

-0.59

POSITIVE LOGITS

igsaw

1.30

umbo

1.22

anky

1.22

ingle

1.19

agged

1.17

umbled

1.17

ammers

1.16

ourn

1.14

upiter

1.12

ockey

1.12

Activations Density 0.024%

words related to movement or action

the letter 'j' in various contexts

No Comments

No Known Activations