INDEX

Explanations

phrases related to consequences or feedback, especially negative ones

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "back" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Parenthood

-0.69

ison

-0.66

aukee

-0.64

inational

-0.62

ijn

-0.60

 ..............

-0.60

Fey

-0.59

entric

-0.58

Kiw

-0.58

ptin

-0.58

POSITIVE LOGITS

stab

1.27

tracking

1.26

dated

1.22

packs

1.20

doors

1.17

packing

1.14

track

1.13

fired

1.12

bones

1.10

gam

1.08

Activations Density 0.041%

phrases related to consequences or feedback, especially negative ones

occurrences of the word "back" and its variations

No Comments

No Known Activations