INDEX

Explanations

scholars and scholarly activities

oai_token-act-pair · gpt-3.5-turbo

references to scholars and scholarly work

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

 Labrador

-0.81

 Ventura

-0.71

 Krypt

-0.62

 territ

-0.60

 chaotic

-0.59

 parade

-0.58

 Bots

-0.58

 Bravo

-0.58

 sunrise

-0.57

 Commodore

-0.57

POSITIVE LOGITS

sonian

1.33

hip

1.08

 scholars

1.03

 scholar

1.01

olars

0.98

 Scholars

0.90

ngth

0.89

itatively

0.88

craft

0.88

 laureate

0.86

Activations Density 0.030%

scholars and scholarly activities

references to scholars and scholarly work

No Comments

No Known Activations