INDEX

Explanations

travel-related terms combined with words indicating a sense of community or togetherness

oai_token-act-pair · gpt-3.5-turbo

mentions of travel and exploration experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asel

-0.75

 Grac

-0.70

eff

-0.70

 retard

-0.67

È

-0.62

 declass

-0.62

reme

-0.62

ear

-0.61

 recovery

-0.60

cephal

-0.60

POSITIVE LOGITS

 Travels

1.15

Ire

0.84

dayName

0.82

 Flavoring

0.81

NetMessage

0.79

tnc

0.76

||||

0.74

 destinations

0.72

loading

0.71

å°Ĩ

0.71

Activations Density 0.016%

travel-related terms combined with words indicating a sense of community or togetherness

mentions of travel and exploration experiences

No Comments

No Known Activations