INDEX

Explanations

words related to negotiation and reaching agreements

oai_token-act-pair · gpt-3.5-turbo

the concept of compromise in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ahon

-0.80

asters

-0.73

stri

-0.72

count

-0.71

adder

-0.71

ighty

-0.71

alia

-0.70

usage

-0.69

runner

-0.69

uni

-0.68

POSITIVE LOGITS

 compromise

0.95

 compromises

0.91

 between

0.81

 compromising

0.79

 negotiators

0.72

romising

0.70

 negotiator

0.70

 comprom

0.69

 stal

0.69

xual

0.68

Activations Density 0.056%

words related to negotiation and reaching agreements

the concept of compromise in various contexts

No Comments

No Known Activations