INDEX

Explanations

explanations or excuses in sentences

oai_token-act-pair · gpt-3.5-turbo

various types of explanations and excuses

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

yard

-0.69

amorph

-0.69

marks

-0.66

Ko

-0.65

arnaev

-0.65

tein

-0.64

ipeg

-0.64

production

-0.64

 Nanto

-0.63

POSITIVE LOGITS

WHY

0.98

why

0.97

why

0.86

abl

0.84

 explanations

0.82

 excuses

0.80

 explanation

0.79

for

0.78

 justifying

0.77

 rationale

0.76

Activations Density 0.083%

explanations or excuses in sentences

various types of explanations and excuses

No Comments

No Known Activations