INDEX

Explanations

personal interactions and conversations

oai_token-act-pair · gpt-3.5-turbo

expressions of personal reflection and experiences

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

 purportedly

-0.49

 substantially

-0.48

 markedly

-0.47

 multinational

-0.44

CLR

-0.44

Analysis

-0.43

cour

-0.43

quartered

-0.42

 sharply

-0.42

pmwiki

-0.42

POSITIVE LOGITS

 fuckin

0.64

 gonna

0.62

laughs

0.60

 fucking

0.59

 wanna

0.55

 gigg

0.52

 guys

0.52

 laughing

0.51

 kinda

0.51

 feeling

0.51

Activations Density 4.625%

personal interactions and conversations

expressions of personal reflection and experiences

No Comments

No Known Activations