INDEX

Explanations

mentions of neighbors and their interactions or characteristics

oai_token-act-pair · gpt-3.5-turbo

references to neighbors in a community context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Role

-0.79

iste

-0.76

 Enhancement

-0.71

 Whilst

-0.71

isation

-0.69

 apologise

-0.69

isable

-0.69

 emphas

-0.69

 Austral

-0.68

utt

-0.66

POSITIVE LOGITS

 neighbors

4.01

 neighbours

3.31

 neighbor

3.13

 neighbour

2.50

Neigh

2.29

 Neighbor

2.28

 Neigh

2.05

 neighboring

1.96

 cousins

1.72

 neighborhood

1.69

Activations Density 0.016%

mentions of neighbors and their interactions or characteristics

references to neighbors in a community context

No Comments

No Known Activations