INDEX

Explanations

phrases indicating a point to remember or keep in mind

oai_token-act-pair · gpt-3.5-turbo

phrases urging readers to stay informed or pay attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iliary

-0.79

ode

-0.77

DragonMagazine

-0.71

NetMessage

-0.66

RES

-0.64

ointed

-0.64

ohydrate

-0.64

omas

-0.62

éĹ

-0.62

ELF

-0.61

POSITIVE LOGITS

 tabs

0.91

 Calm

0.87

 track

0.86

 vigil

0.82

 scrolling

0.79

 tuned

0.78

 kosher

0.77

 vigilance

0.76

akes

0.76

 calm

0.75

Activations Density 0.031%

phrases indicating a point to remember or keep in mind

phrases urging readers to stay informed or pay attention

No Comments

No Known Activations