INDEX

Explanations

words related to football programs or teams

oai_token-act-pair · gpt-3.5-turbo

references to specific college football programs and teams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

block

-0.74

 compartment

-0.72

orders

-0.68

 drip

-0.67

VAT

-0.67

 ponies

-0.66

 Panzer

-0.64

mentioned

-0.64

 orders

-0.63

 authorised

-0.63

POSITIVE LOGITS

 Athletic

1.11

 Athletics

1.11

 athletics

1.05

 athletic

0.97

 alum

0.95

keyes

0.95

 Bulldogs

0.91

 University

0.88

 Wildcats

0.87

 Bears

0.86

Activations Density 0.152%

words related to football programs or teams

references to specific college football programs and teams

No Comments

No Known Activations