INDEX

Explanations

terms related to technology and features available in devices

oai_token-act-pair · gpt-3.5-turbo

phrases that highlight recommendations or useful tools

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

SPONSORED

-0.72

entially

-0.67

 detriment

-0.66

 adversely

-0.65

 falsely

-0.65

 repud

-0.64

 negatively

-0.64

 subord

-0.64

ificantly

-0.64

 remainder

-0.63

POSITIVE LOGITS

 funky

0.80

ðŁĳ

0.77

bang

0.77

itty

0.74

ya

0.73

!.

0.72

 goodies

0.69

 classy

0.69

fun

0.68

 sweet

0.68

Activations Density 0.397%

terms related to technology and features available in devices

phrases that highlight recommendations or useful tools

No Comments

No Known Activations