INDEX

Explanations

mentions of memories or memoirs

oai_token-act-pair · gpt-3.5-turbo

mentions of "memory" or related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ASC

-0.73

 Highlander

-0.65

 diver

-0.65

 Galile

-0.65

 unequal

-0.64

 Ducks

-0.64

 Icelandic

-0.64

 Nordic

-0.63

 Aval

-0.63

 Shining

-0.63

POSITIVE LOGITS

oir

1.38

phis

1.36

orial

1.17

pty

1.12

oria

1.12

achine

1.12

eor

1.12

orable

1.11

elong

1.10

oleon

1.09

Activations Density 0.015%

mentions of memories or memoirs

mentions of "memory" or related terms

No Comments

No Known Activations