INDEX

Explanations

phrases related to approvals or permission

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "green light," indicating permission or approval

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Mehran

-0.72

ersive

-0.64

oln

-0.64

 Cousins

-0.63

etsk

-0.63

qv

-0.62

================================================================

-0.61

enne

-0.61

ersion

-0.60

 visiting

-0.59

POSITIVE LOGITS

lights

0.91

light

0.73

enment

0.73

beam

0.73

edly

0.72

 rods

0.72

 shone

0.70

 beam

0.69

estones

0.69

 fixtures

0.68

Activations Density 0.017%

phrases related to approvals or permission

phrases related to the concept of "green light," indicating permission or approval

No Comments

No Known Activations