INDEX

Explanations

words related to beaches

oai_token-act-pair · gpt-3.5-turbo

mentions of the beach

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

ilyn

-0.76

ativity

-0.72

Interstitial

-0.71

encers

-0.69

icates

-0.68

å£«

-0.67

ioch

-0.67

æł

-0.66

ÑĮ

-0.65

avery

-0.64

POSITIVE LOGITS

front

1.10

goers

1.07

side

1.05

 volleyball

0.99

 beach

0.94

walk

0.87

 Beach

0.86

 Resort

0.83

tub

0.83

plane

0.82

Activations Density 0.009%

words related to beaches

mentions of the beach

No Comments

No Known Activations