INDEX

Explanations

words related to transportation infrastructure, specifically roads and vehicles

oai_token-act-pair · gpt-3.5-turbo

words related to transportation and vehicles

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

Nur

-0.70

imov

-0.68

 STATS

-0.67

 Milan

-0.63

 Maharashtra

-0.60

ãĤ¢

-0.60

-0.59

 Proposition

-0.58

POSITIVE LOGITS

culosis

1.00

oshenko

0.91

ulhu

0.85

nel

0.81

umatic

0.80

obl

0.78

_>

0.77

emouth

0.75

hiba

0.74

ilight

0.73

Activations Density 0.074%

words related to transportation infrastructure, specifically roads and vehicles

words related to transportation and vehicles

No Comments

No Known Activations