INDEX

Explanations

locations or places described as 'nearby'

oai_token-act-pair · gpt-3.5-turbo

the term "nearby" indicating proximity to objects or locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icer

-0.79

istry

-0.78

xml

-0.77

ppe

-0.77

chin

-0.77

skill

-0.74

xy

-0.74

xx

-0.74

apego

-0.73

zai

-0.72

POSITIVE LOGITS

 neighbor

0.96

 vicinity

0.92

 neighbors

0.92

 nearby

0.89

 neighbour

0.87

 neighbours

0.81

 apartment

0.76

 waterways

0.74

 town

0.74

 suburbs

0.74

Activations Density 0.028%

locations or places described as 'nearby'

the term "nearby" indicating proximity to objects or locations

No Comments

No Known Activations