INDEX

Explanations

patterns of characters that suggest URLs or links

oai_token-act-pair · gpt-3.5-turbo

words related to chocolate and its quality or condition

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

buster

-0.76

 VIEW

-0.74

 Hutchinson

-0.69

 buckle

-0.66

VK

-0.65

 figure

-0.64

WOR

-0.64

 Grayson

-0.63

 Forsaken

-0.63

 Feldman

-0.63

POSITIVE LOGITS

onial

1.16

ocol

1.00

atem

0.99

acco

0.98

avored

0.93

urized

0.91

oria

0.89

orius

0.87

ongyang

0.85

ates

0.85

Activations Density 0.026%

patterns of characters that suggest URLs or links

words related to chocolate and its quality or condition

No Comments

No Known Activations