INDEX

Explanations

positive adjectives denoting something remarkable or exceptional

oai_token-act-pair · gpt-3.5-turbo

descriptors that denote excellence or outstanding qualities

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

©¶æ

-0.76

ATA

-0.76

eper

-0.75

aper

-0.73

enhagen

-0.71

claimer

-0.71

ueller

-0.71

cling

-0.70

hers

-0.70

SO

-0.69

POSITIVE LOGITS

 feats

1.32

 feat

1.09

 accomplishment

1.09

 achievement

1.06

 accomplishments

1.01

 achievements

1.00

 coincidence

0.98

 transformations

0.93

 creations

0.89

 rendition

0.87

Activations Density 0.113%

positive adjectives denoting something remarkable or exceptional

descriptors that denote excellence or outstanding qualities

No Comments

No Known Activations