INDEX

Explanations

mentions of daily activities or routines

oai_token-act-pair · gpt-3.5-turbo

references to daily routines or practices

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

holes

-0.96

essee

-0.88

atchewan

-0.78

 Gould

-0.77

artisan

-0.76

hole

-0.75

aine

-0.74

OHN

-0.73

eer

-0.72

erala

-0.72

POSITIVE LOGITS

motion

1.03

 occurrence

0.92

 commute

0.86

 ration

0.82

 intervals

0.81

 basis

0.80

 cycle

0.79

 routines

0.79

 thereafter

0.79

 occurrences

0.78

Activations Density 0.018%

mentions of daily activities or routines

references to daily routines or practices

No Comments

No Known Activations