INDEX

Explanations

terms related to confirmation or certainty

oai_token-act-pair · gpt-3.5-turbo

references to business, losses, and significant outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 eleph

-0.62

 confir

-0.62

 extract

-0.62

 redistributed

-0.57

 cann

-0.56

 outwe

-0.56

 seiz

-0.56

 spons

-0.55

 ende

-0.55

 borne

-0.54

POSITIVE LOGITS

,-

1.00

0.94

,...

0.84

Merit

0.82

)=(

0.79

,,

0.78

KEN

0.76

,.

0.76

opian

0.75

PIN

0.74

Activations Density 0.304%

terms related to confirmation or certainty

references to business, losses, and significant outcomes

No Comments

No Known Activations