INDEX

Explanations

phrases related to positive attributes or characteristics

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize qualitative attributes or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

most

-0.63

assi

-0.62

 imprint

-0.62

=[

-0.61

 ambassador

-0.59

 Ambassador

-0.59

pressed

-0.58

 Skies

-0.57

sometimes

-0.57

adobe

-0.56

POSITIVE LOGITS

abal

0.79

osher

0.76

ostic

0.74

artment

0.69

Ò

0.69

à©

0.69

opathic

0.68

WER

0.68

usional

0.67

ubes

0.66

Activations Density 0.250%

phrases related to positive attributes or characteristics

phrases that emphasize qualitative attributes or classifications

No Comments

No Known Activations