INDEX

Explanations

references to close physical distance between objects or individuals

oai_token-act-pair · gpt-3.5-turbo

terms related to physical closeness or distance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

oz

-0.68

sted

-0.64

igan

-0.64

lich

-0.63

igger

-0.62

Der

-0.61

 wonders

-0.61

Files

-0.61

 Fool

-0.60

ida

-0.59

POSITIVE LOGITS

 proximity

3.73

imity

2.04

 vicinity

1.85

 distance

1.43

 clos

1.30

 location

1.25

 presence

1.20

 familiarity

1.19

 similarity

1.15

 surroundings

1.14

Activations Density 0.012%

references to close physical distance between objects or individuals

terms related to physical closeness or distance

No Comments

No Known Activations