INDEX

Explanations

mentions of the word "Cor" followed by another word

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Cor" as a reference or topic within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lihood

-0.95

CRIP

-0.82

terday

-0.78

ï¸

-0.74

Magikarp

-0.74

TPS

-0.72

INESS

-0.72

éĹĺ

-0.71

WARE

-0.70

 Dangerous

-0.67

POSITIVE LOGITS

rupt

1.18

ruption

1.14

rigan

1.11

rupted

1.11

fman

1.11

relation

1.10

porate

1.08

bis

1.05

bett

1.04

relations

1.00

Activations Density 0.020%

mentions of the word "Cor" followed by another word

occurrences of the term "Cor" as a reference or topic within a document

No Comments

No Known Activations