INDEX

Explanations

references to specific names (possibly surnames)

oai_token-act-pair · gpt-3.5-turbo

the names of individuals, particularly those relevant to specific contexts or events

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

meric

-0.75

 Doodle

-0.71

ours

-0.69

fruit

-0.65

 carts

-0.62

iates

-0.61

gamer

-0.61

 Pony

-0.61

grading

-0.61

mediate

-0.61

POSITIVE LOGITS

 Andersen

1.19

quist

1.05

ensen

1.00

sson

1.00

Bj

0.99

qv

0.98

 Sven

0.96

lund

0.95

ersen

0.95

gaard

0.91

Activations Density 0.034%

references to specific names (possibly surnames)

the names of individuals, particularly those relevant to specific contexts or events

No Comments

No Known Activations