INDEX

Explanations

numerical values or codes within a text document

oai_token-act-pair · gpt-3.5-turbo

numerical values and technical specifications

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

ufact

-0.73

 whisk

-0.70

andestine

-0.67

 shovel

-0.65

sho

-0.65

CRA

-0.63

 Colt

-0.62

 gren

-0.62

 teasp

-0.61

 rushed

-0.61

POSITIVE LOGITS

Edit

0.82

entric

0.72

VEN

0.71

TION

0.70

âĢ²

0.69

CLUS

0.69

hyde

0.68

PORT

0.68

FIX

0.67

hex

0.67

Activations Density 0.062%

numerical values or codes within a text document

numerical values and technical specifications

No Comments

No Known Activations