INDEX

Explanations

references to tours, events or activities happening in a particular location

oai_token-act-pair · gpt-3.5-turbo

references to tours

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

 loose

-0.72

iod

-0.68

 fluid

-0.65

 clustered

-0.64

 thriving

-0.64

 procedural

-0.64

 predictive

-0.63

ever

-0.63

srf

-0.62

ntax

-0.62

POSITIVE LOGITS

neys

1.16

 tour

1.09

ney

1.04

 tours

0.99

neau

0.94

 Tour

0.94

 touring

0.92

 Tours

0.90

 TOUR

0.83

efully

0.83

Activations Density 0.014%

references to tours, events or activities happening in a particular location

references to tours

No Comments

No Known Activations