INDEX

Explanations

specific numbers in the context of descriptions or instructions

oai_token-act-pair · gpt-3.5-turbo

references to specific projects or initiatives being discussed

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

 suppose

-0.76

 namely

-0.74

\'

-0.69

 wondered

-0.69

 certainly

-0.68

ingly

-0.67

 alike

-0.67

!!!

-0.66

ettings

-0.66

???

-0.65

POSITIVE LOGITS

 remainder

1.25

 entire

1.09

 same

1.08

 entirety

1.07

 next

1.07

 upcoming

1.05

 nation

0.99

 rest

0.98

 fullest

0.98

 foreseeable

0.97

Activations Density 0.828%

specific numbers in the context of descriptions or instructions

references to specific projects or initiatives being discussed

No Comments

No Known Activations