INDEX

Explanations

terms related to interrupted dialogue, specifically with the structure "I said" followed by exclamatory punctuation

oai_token-act-pair · gpt-3.5-turbo

repeated phrases or expressions that convey strong emotions or sentiments

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

 Reprodu

-0.71

 spectrum

-0.70

 Skydragon

-0.69

MFT

-0.69

 commercially

-0.67

 range

-0.65

 classification

-0.65

 precip

-0.64

 Mous

-0.64

 shroud

-0.64

POSITIVE LOGITS

ª

1.50

ł

1.48

¹

1.39

Ķ

1.30

Ĳ

1.30

³

1.30

ĳ

1.28

©

1.26

¡

1.26

ľ

1.25

Activations Density 0.124%

terms related to interrupted dialogue, specifically with the structure "I said" followed by exclamatory punctuation

repeated phrases or expressions that convey strong emotions or sentiments

No Comments

No Known Activations