INDEX

Explanations

phrases related to actions or decisions being taken

oai_token-act-pair · gpt-3.5-turbo

references to undefined or ambiguous concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 palm

-0.79

 oven

-0.78

 barr

-0.74

mum

-0.71

 indemn

-0.70

 handic

-0.70

 mail

-0.70

 Lumpur

-0.68

 nuts

-0.68

 pronoun

-0.68

POSITIVE LOGITS

meaning

1.33

that

1.30

especially

1.28

these

1.28

perhaps

1.28

which

1.27

they

1.26

particularly

1.26

including

1.24

feat

1.23

Activations Density 0.077%

phrases related to actions or decisions being taken

references to undefined or ambiguous concepts

No Comments

No Known Activations