INDEX

Explanations

references to time periods, particularly phrases indicating a duration of many years

oai_token-act-pair · gpt-3.5-turbo

references to duration or the passage of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

notice

-0.78

alg

-0.77

obin

-0.76

addons

-0.76

Notice

-0.73

imate

-0.72

ella

-0.71

depth

-0.69

ops

-0.69

asy

-0.69

POSITIVE LOGITS

ago

0.81

 thereafter

0.70

now

0.66

 afterward

0.64

SPONSORED

0.64

 mathematic

0.63

 dreamed

0.63

Ago

0.62

 prior

0.62

 waged

0.61

Activations Density 0.085%

references to time periods, particularly phrases indicating a duration of many years

references to duration or the passage of time

No Comments

No Known Activations