INDEX

Explanations

the word "daily."

oai_token-act-pair · gpt-3.5-turbo

references to daily activities or routines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

holes

-0.96

essee

-0.87

 Gould

-0.83

OHN

-0.82

artisan

-0.80

dinand

-0.78

hole

-0.77

atchewan

-0.77

eer

-0.76

erala

-0.75

POSITIVE LOGITS

motion

1.12

 occurrence

0.97

 occurrences

0.85

 dose

0.85

 necessities

0.84

 servings

0.84

 routines

0.82

 commute

0.82

 intervals

0.81

 basis

0.80

Activations Density 0.023%

the word "daily."

references to daily activities or routines

No Comments

No Known Activations