INDEX

Explanations

time-related expressions indicating a duration or a specific point in time

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a time reference or continuity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

BILITIES

-0.68

enberg

-0.66

STAR

-0.65

alogy

-0.65

estones

-0.65

aspx

-0.65

adi

-0.64

================================

-0.64

abus

-0.63

avis

-0.62

POSITIVE LOGITS

rely

0.77

 inception

0.77

 adolescence

0.65

 Hiroshima

0.64

 mastering

0.63

isSpecialOrderable

0.62

ĸļ

0.61

 Keller

0.61

 inauguration

0.60

 adolesc

0.60

Activations Density 0.034%

time-related expressions indicating a duration or a specific point in time

phrases that indicate a time reference or continuity

No Comments

No Known Activations