INDEX

Explanations

languages

oai_token-act-pair · gpt-3.5-turbo

non-verbal content related to digital communication or formatting

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

iott

-0.74

bringer

-0.72

berger

-0.64

atten

-0.64

ilon

-0.63

 tempted

-0.62

 pigeon

-0.61

bert

-0.60

mens

-0.60

arer

-0.60

POSITIVE LOGITS

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

0.79

ÂłÂłÂłÂł

0.71

Constructed

0.71

TEXTURE

0.69

âĵĺ

0.69

oglu

0.68

OOOOOOOO

0.67

Introduced

0.66

ÂłÂłÂł

0.65

Activations Density 0.147%

languages

non-verbal content related to digital communication or formatting

No Comments

No Known Activations