INDEX

Explanations

dates and events mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ological

-0.59

 Millions

-0.59

 Individuals

-0.59

 Reports

-0.57

 Extend

-0.57

arming

-0.57

 Mountains

-0.57

 invocation

-0.57

 Individual

-0.57

 Achieve

-0.56

POSITIVE LOGITS

nt

1.02

hers

1.02

 definitely

0.95

hes

0.82

 certainly

0.82

wolf

0.80

 probably

0.76

not

0.76

wolves

0.75

 indeed

0.74

Activations Density 0.412%

dates and events mentioned in the text

instances of the verb "was."

No Comments

No Known Activations