INDEX

Explanations

mentions of memories or memoirs

oai_token-act-pair · gpt-3.5-turbo

references to memories or memoirs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ASC

-0.73

 Aval

-0.68

 Highlander

-0.63

 Ducks

-0.62

 diver

-0.60

 Citizen

-0.60

 Palmer

-0.60

 Elves

-0.60

 Drift

-0.59

 Shining

-0.59

POSITIVE LOGITS

phis

1.40

oir

1.32

abilia

1.17

etics

1.16

etic

1.15

orial

1.15

eor

1.14

elong

1.13

bered

1.11

orable

1.10

Activations Density 0.022%

mentions of memories or memoirs

references to memories or memoirs

No Comments

No Known Activations