INDEX

Explanations

phrases comparing things or actions as being similar or closely related

oai_token-act-pair · gpt-3.5-turbo

comparisons and analogies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Published

-0.73

 Mush

-0.69

 Monica

-0.68

å£«

-0.63

 residency

-0.61

 Handbook

-0.61

ãĤ¡

-0.60

 leaflets

-0.58

ainer

-0.58

 SATA

-0.58

POSITIVE LOGITS

lihood

1.34

entimes

0.96

ened

0.95

mares

0.89

ensing

0.82

terness

0.81

ening

0.80

ravity

0.75

etheless

0.74

gypt

0.74

Activations Density 0.026%

phrases comparing things or actions as being similar or closely related

comparisons and analogies

No Comments

No Known Activations