INDEX

Explanations

numeric words

oai_token-act-pair · gpt-3.5-turbo

mentions of numerical quantities and ages

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

geist

-0.68

vantage

-0.68

HY

-0.68

Hub

-0.68

/_

-0.67

mite

-0.66

ACTION

-0.66

lance

-0.65

DH

-0.64

trap

-0.64

POSITIVE LOGITS

teenth

1.69

teen

1.50

eenth

1.44

fold

1.40

een

1.37

 hundred

1.35

 thousand

1.19

 months

1.16

aciously

1.14

ieth

1.14

Activations Density 0.109%

numeric words

mentions of numerical quantities and ages

No Comments

No Known Activations