INDEX

Explanations

mentions of time spent on various activities or places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "spent"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Seymour

-0.64

ĪĴ

-0.61

ensen

-0.60

 Watson

-0.57

usable

-0.57

eat

-0.56

 abhor

-0.56

 caveat

-0.56

Come

-0.56

 Conan

-0.56

POSITIVE LOGITS

itures

0.93

IPM

0.88

 spent

0.86

lav

0.86

 Spend

0.83

edIn

0.80

 abroad

0.79

iture

0.77

 Spending

0.77

 redes

0.72

Activations Density 0.026%

mentions of time spent on various activities or places

occurrences of the word "spent"

No Comments

No Known Activations