INDEX

Explanations

proper names or mentions of the name "Cor" followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Cor" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.90

terday

-0.80

CRIP

-0.80

éĹĺ

-0.79

WARE

-0.74

INESS

-0.74

 Difficulty

-0.71

WAYS

-0.69

anwhile

-0.69

CLASSIFIED

-0.66

POSITIVE LOGITS

rigan

1.10

rupt

1.10

ruption

1.07

relation

1.05

rupted

1.02

porate

1.01

byn

1.00

fman

1.00

bis

0.99

ros

0.99

Activations Density 0.008%

proper names or mentions of the name "Cor" followed by a number

mentions of the name "Cor" in various contexts

No Comments

No Known Activations