INDEX

Explanations

references to notable individuals in various contexts

oai_token-act-pair · gpt-3.5-turbo

commas and punctuation marks in the text

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

EngineDebug

-0.84

Characters

-0.82

raq

-0.73

odes

-0.73

Examples

-0.73

ãĥ¥

-0.70

ocry

-0.69

ioxid

-0.69

ILLE

-0.67

FIX

-0.67

POSITIVE LOGITS

 founder

1.26

aka

1.24

Jr

1.22

who

1.20

 grandson

1.18

 chairman

1.16

 president

1.15

 whose

1.13

 propriet

1.12

 formerly

1.09

Activations Density 0.212%

references to notable individuals in various contexts

commas and punctuation marks in the text

No Comments

No Known Activations