INDEX

Explanations

mentions of the name "Edwards" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the name "Edwards" in relation to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

efully

-0.80

ãĥĥãĥĪ

-0.72

apest

-0.71

fully

-0.70

ronic

-0.70

Ľ

-0.69

ãĥĩãĤ£

-0.67

ASE

-0.65

FUL

-0.65

zzi

-0.64

POSITIVE LOGITS

pires

1.01

 Edwards

0.99

monton

0.90

burgh

0.87

ville

0.76

endale

0.74

 confir

0.71

reys

0.71

bury

0.70

sburg

0.70

Activations Density 0.005%

mentions of the name "Edwards" in various contexts

the name "Edwards" in relation to various contexts

No Comments

No Known Activations