INDEX

Explanations

technical computer-related terms, specifically focusing on processors

oai_token-act-pair · gpt-3.5-turbo

references to octopus-related themes

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

Interstitial

-1.04

culosis

-0.85

HCR

-0.76

ACTED

-0.75

ãģĦ

-0.68

 Hots

-0.68

 Tycoon

-0.68

adder

-0.67

 Responsibility

-0.66

 Limbaugh

-0.64

POSITIVE LOGITS

opus

1.51

agonal

1.14

oct

1.11

agon

1.11

ober

1.04

ave

0.97

urnal

0.92

uple

0.92

osed

0.92

agons

0.91

Activations Density 0.012%

technical computer-related terms, specifically focusing on processors

references to octopus-related themes

No Comments

No Known Activations