INDEX

Explanations

names or terms related to "Griffith."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Griffith" or related terms

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

Ø§ÙĦ

-0.72

ounded

-0.71

essional

-0.70

AAF

-0.68

Ø¯

-0.67

 Pastebin

-0.66

ctica

-0.64

ãĥ¤

-0.64

 Scotia

-0.63

OPLE

-0.63

POSITIVE LOGITS

 Griffith

1.26

0.86

shire

0.85

 Observatory

0.81

wip

0.79

sv

0.78

 Scully

0.76

enhagen

0.75

icides

0.75

sburg

0.74

Activations Density 0.014%

names or terms related to "Griffith."

mentions of the name "Griffith" or related terms

No Comments

No Known Activations