INDEX

Explanations

details related to specific physical actions or events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "with."

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

cent

-0.83

fair

-0.75

hops

-0.75

ghai

-0.73

pring

-0.68

ovich

-0.67

sburg

-0.66

hower

-0.65

pton

-0.64

uki

-0.63

POSITIVE LOGITS

stood

1.19

 regards

1.13

 impunity

1.13

 regard

1.09

drawn

1.09

draw

1.06

standing

0.99

holding

0.99

 respect

0.96

 dignity

0.88

Activations Density 0.171%

details related to specific physical actions or events

instances of the word "with."

No Comments

No Known Activations