INDEX

Explanations

words related to vision and sight

oai_token-act-pair · gpt-3.5-turbo

the presence of words that contain the string "ight"

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

å¥³

-0.96

PsyNetMessage

-0.94

accompan

-0.88

itaire

-0.81

qv

-0.81

senal

-0.74

ãĥīãĥ©ãĤ´ãĥ³

-0.70

berman

-0.70

Filename

-0.68

POSITIVE LOGITS

mares

1.28

mare

0.95

seeing

0.93

enment

0.91

edly

0.88

ened

0.84

ful

0.84

ead

0.81

edIn

0.81

eyed

0.81

Activations Density 0.025%

words related to vision and sight

the presence of words that contain the string "ight"

No Comments

No Known Activations