INDEX

Explanations

explanatory statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to explaining concepts or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ngth

-0.82

ille

-0.75

emies

-0.75

kus

-0.72

sembly

-0.70

jab

-0.67

ontent

-0.66

 Instruments

-0.66

ctors

-0.65

opers

-0.63

POSITIVE LOGITS

why

1.65

why

1.33

WHY

1.31

how

0.96

 discrepancies

0.92

Why

0.88

 inconsistencies

0.87

Why

0.84

 explanations

0.81

 disapp

0.80

Activations Density 0.052%

explanatory statements

phrases related to explaining concepts or phenomena

No Comments

No Known Activations