INDEX

Explanations

expressions related to authority, decision-making, and responsibility

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

onyms

-0.82

idered

-0.75

 acquaintances

-0.74

types

-0.72

erald

-0.69

osponsors

-0.69

cia

-0.67

rentices

-0.67

olid

-0.67

iety

-0.66

POSITIVE LOGITS

 overseeing

1.13

 brunt

1.04

 responsibility

0.96

 respons

0.90

 superv

0.86

 oversee

0.82

 reins

0.82

 orchestr

0.82

orship

0.82

 approving

0.79

Activations Density 0.733%

expressions related to authority, decision-making, and responsibility

No Comments

No Known Activations