INDEX

Explanations

positive attributes or qualities attributed to entities or individuals

oai_token-act-pair · gpt-3.5-turbo

words related to qualities and characteristics

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

dos

-0.76

analysis

-0.71

inav

-0.67

NAS

-0.66

raid

-0.64

MG

-0.63

cross

-0.63

DO

-0.63

space

-0.62

carry

-0.62

POSITIVE LOGITS

 qualities

1.11

 traits

0.96

 virtues

0.93

 talents

0.82

 merits

0.81

wcsstore

0.78

 charact

0.75

 trait

0.74

hovah

0.71

 adject

0.69

Activations Density 0.027%

positive attributes or qualities attributed to entities or individuals

words related to qualities and characteristics

No Known Activations