INDEX

Explanations

words with 'l' appearing multiple times in a row

oai_token-act-pair · gpt-3.5-turbo

terms related to intensity or severity

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

 fluor

-0.70

 vigilance

-0.65

ĻĤ

-0.63

 irony

-0.59

ADRA

-0.59

 ultras

-0.58

 watershed

-0.58

 illusions

-0.57

 Marble

-0.57

 Cycle

-0.57

POSITIVE LOGITS

ndra

0.85

inki

0.82

hesive

0.73

vre

0.73

arnaev

0.72

rero

0.68

sylv

0.67

soType

0.66

uler

0.65

azo

0.65

Activations Density 0.079%

words with 'l' appearing multiple times in a row

terms related to intensity or severity

No Comments

No Known Activations