INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those with the suffixes 'athan' and 'kan'

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.76

Nap

-0.75

soDeliveryDate

-0.70

çīĪ

-0.68

CRIP

-0.67

 Hosp

-0.66

 Widow

-0.66

Fib

-0.66

 Clarks

-0.64

olly

-0.63

POSITIVE LOGITS

adian

0.95

enei

0.93

ovan

0.84

pour

0.82

ista

0.82

ovich

0.80

 Uriel

0.78

atan

0.76

athan

0.76

raph

0.75

Activations Density 0.019%

names of people

names of individuals, particularly those with the suffixes 'athan' and 'kan'

No Known Activations