INDEX

Explanations

statements indicating a return to a previous or original state

oai_token-act-pair · gpt-3.5-turbo

references to recovery or restoration processes

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

nikov

-0.72

andals

-0.70

igated

-0.64

 bureaucracy

-0.63

udos

-0.63

 divor

-0.62

neys

-0.62

llo

-0.61

hoe

-0.61

 anecdotes

-0.61

POSITIVE LOGITS

 equilibrium

1.22

 position

1.19

 optimum

1.08

 shape

1.03

shape

1.02

 optimal

0.99

 normal

0.98

normal

0.98

Position

0.98

Pos

0.95

Activations Density 0.296%

statements indicating a return to a previous or original state

references to recovery or restoration processes

No Comments

No Known Activations