INDEX

Explanations

references to corporations or organizations with an '&' symbol in their names

oai_token-act-pair · gpt-3.5-turbo

references to specific brands or entities associated with the letter "S."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

etheless

-0.74

owicz

-0.73

 Nebula

-0.67

ogene

-0.65

 nexus

-0.65

 orche

-0.64

theless

-0.62

orescence

-0.62

verend

-0.62

lihood

-0.62

POSITIVE LOGITS

Cs

0.88

Bs

0.87

HI

0.82

Co

0.80

RD

0.79

AAA

0.77

RT

0.76

TA

0.75

Vs

0.74

¹

0.74

Activations Density 0.012%

references to corporations or organizations with an '&' symbol in their names

references to specific brands or entities associated with the letter "S."

No Comments

No Known Activations