INDEX

Explanations

words related to rules, instructions, advice, or conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to conditions, prerequisites, and qualifiers

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

sung

-0.78

SPL

-0.77

gew

-0.71

ishi

-0.70

 Schwar

-0.68

 Hobby

-0.67

mens

-0.66

Sold

-0.66

mbuds

-0.65

irlf

-0.65

POSITIVE LOGITS

requisite

0.83

aneously

0.79

requisites

0.79

xual

0.77

aneous

0.74

iously

0.70

itious

0.69

 logically

0.67

 decrypt

0.66

existing

0.65

Activations Density 0.116%

words related to rules, instructions, advice, or conditions

terms related to conditions, prerequisites, and qualifiers

No Comments

No Known Activations