INDEX

Explanations

words ending in 'ness'

oai_token-act-pair · gpt-3.5-turbo

terms related to various aspects of "ness."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

chnology

-0.79

rament

-0.73

zynski

-0.70

ther

-0.69

veyard

-0.69

reon

-0.68

udeb

-0.67

vice

-0.66

olan

-0.64

agall

-0.64

POSITIVE LOGITS

iness

1.04

ness

0.88

fulness

0.85

0.84

lessness

0.83

ledged

0.75

ï¸

0.72

istence

0.72

iest

0.71

ful

0.69

Activations Density 0.028%

words ending in 'ness'

terms related to various aspects of "ness."

No Comments

No Known Activations