INDEX

Explanations

jeep-related terms

oai_token-act-pair · gpt-3.5-turbo

the name "jeep" and variations of the name "je" commonly found in certain contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ´ãĤ¡

-0.80

Interstitial

-0.77

sworth

-0.75

ciating

-0.73

dayName

-0.72

MpServer

-0.71

å¥³

-0.70

ctica

-0.69

Gameplay

-0.69

 weap

-0.68

POSITIVE LOGITS

hovah

1.62

je

0.92

ijn

0.89

neys

0.87

ep

0.80

ff

0.77

ered

0.76

ques

0.74

eps

0.74

 Schwe

0.73

Activations Density 0.012%

jeep-related terms

the name "jeep" and variations of the name "je" commonly found in certain contexts

No Comments

No Known Activations