INDEX

Explanations

specific days of the week

oai_token-act-pair · gpt-3.5-turbo

references to specific days of the week

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

allo

-0.88

kef

-0.82

abet

-0.81

umbn

-0.81

Adds

-0.80

onductor

-0.78

agos

-0.75

nih

-0.74

ris

-0.72

raltar

-0.71

POSITIVE LOGITS

 nights

1.19

 mornings

1.12

 evenings

1.09

 afternoon

1.07

 morning

1.04

days

1.02

 night

1.01

 evening

1.00

DAY

0.96

 Night

0.93

Activations Density 0.092%

specific days of the week

references to specific days of the week

No Comments

No Known Activations