INDEX

Explanations

sports-related terms and names

oai_token-act-pair · gpt-3.5-turbo

specific numerical data or statistics related to events or entities

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

 contingency

-0.69

nesday

-0.64

 footing

-0.60

 blockers

-0.60

 comprom

-0.57

 intervening

-0.56

 showc

-0.56

 narrowing

-0.56

 reper

-0.56

 assum

-0.55

POSITIVE LOGITS

 âĵĺ

1.04

Joined

0.86

 Died

0.72

itars

0.71

Offline

0.71

 Posts

0.63

Posts

0.62

ËĪ

0.61

Legendary

0.61

 âĺħ

0.59

Activations Density 0.569%

sports-related terms and names

specific numerical data or statistics related to events or entities

No Comments

No Known Activations