INDEX

Explanations

names of people with their professional titles

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically commas, which suggest lists or separations in context

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

enhagen

-0.70

endo

-0.68

ixir

-0.65

opathy

-0.62

position

-0.61

FIX

-0.61

="/

-0.60

algia

-0.59

growth

-0.59

IMP

-0.59

POSITIVE LOGITS

 respectively

2.09

depending

1.01

 alike

0.97

 whichever

0.83

Jr

0.79

Sr

0.78

 depending

0.76

Jr

0.76

etc

0.73

LLP

0.70

Activations Density 0.247%

names of people with their professional titles

punctuation marks, specifically commas, which suggest lists or separations in context

No Comments

No Known Activations