INDEX

Explanations

names and titles related to corporate executives

oai_token-act-pair · gpt-3.5-turbo

references to chief executives and their positions

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

 Parenthood

-0.71

::::::::

-0.66

ankind

-0.65

atever

-0.63

NRS

-0.60

selves

-0.60

cgi

-0.60

NULL

-0.59

STER

-0.59

Sensor

-0.57

POSITIVE LOGITS

 officer

0.91

 Officer

0.90

oft

0.77

 strategist

0.70

ahoo

0.68

hip

0.66

 realised

0.64

 aspir

0.63

 contender

0.62

 lett

0.62

Activations Density 0.072%

names and titles related to corporate executives

references to chief executives and their positions

No Comments

No Known Activations