INDEX

Explanations

words related to qualities or attributes ending in 'ness'

oai_token-act-pair · gpt-3.5-turbo

terms related to various forms of 'ness' indicating qualities or states

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

Not in Any Lists

No Comments

Negative Logits

TOR

-0.65

reon

-0.64

iov

-0.63

ther

-0.62

olan

-0.61

avez

-0.60

Capt

-0.59

inav

-0.59

otta

-0.59

oston

-0.58

POSITIVE LOGITS

fulness

1.01

iness

1.00

ness

0.95

ibility

0.87

lessness

0.86

eness

0.84

nesses

0.81

uality

0.80

iveness

0.78

entials

0.77

Activations Density 0.021%

words related to qualities or attributes ending in 'ness'

terms related to various forms of 'ness' indicating qualities or states

No Comments

No Known Activations