INDEX

Explanations

time-related phrases or time spans

oai_token-act-pair · gpt-3.5-turbo

references to specific time periods and their comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

xs

-0.61

nos

-0.61

 floats

-0.60

 libertarians

-0.59

 curses

-0.59

 Scores

-0.59

facts

-0.57

rine

-0.56

 Cards

-0.54

 Bits

-0.54

POSITIVE LOGITS

 period

1.63

 timeframe

1.55

 span

1.51

 time

1.36

period

1.24

 interval

1.19

 periods

1.08

 stretch

1.06

era

1.06

 Period

0.99

Activations Density 0.118%

time-related phrases or time spans

references to specific time periods and their comparisons

No Comments

No Known Activations