INDEX

Explanations

specific years and numbers related to events or quantities

oai_token-act-pair · gpt-3.5-turbo

mentions of authority figures and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ngth

-0.84

escription

-0.80

ritis

-0.77

ocate

-0.74

atron

-0.73

adiq

-0.72

encers

-0.70

gars

-0.69

haar

-0.69

oulos

-0.68

POSITIVE LOGITS

 basis

1.27

 occasions

1.21

 behalf

1.14

 occasion

0.97

 doorstep

0.94

 grounds

0.94

 footing

0.91

 pretext

0.88

 website

0.87

 bandwagon

0.84

Activations Density 0.795%

specific years and numbers related to events or quantities

mentions of authority figures and institutions

No Comments

No Known Activations