INDEX

Explanations

scheduled events or activities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating scheduled future events

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

asso

-0.71

minus

-0.70

MJ

-0.68

arc

-0.67

heart

-0.65

neck

-0.65

pill

-0.65

athy

-0.65

founded

-0.64

eth

-0.64

POSITIVE LOGITS

geries

1.15

gery

0.98

bidden

0.88

 informational

0.81

 conting

0.80

 emergencies

0.80

 inclusion

0.79

 heights

0.77

 renewal

0.75

WARD

0.73

Activations Density 0.151%

scheduled events or activities

phrases indicating scheduled future events

No Comments

No Known Activations