INDEX

Explanations

instances of the word 'interaction'

oai_token-act-pair · gpt-3.5-turbo

references to various forms of interaction

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

ews

-0.74

 Century

-0.68

İĭ

-0.68

enda

-0.66

ilts

-0.66

liga

-0.65

sa

-0.64

 bankrupt

-0.64

å¤©

-0.64

 proudly

-0.62

POSITIVE LOGITS

 interaction

3.68

 interactions

3.01

 interacting

2.19

 interact

2.11

 interacted

1.99

 interacts

1.84

 encounter

1.61

 encounters

1.45

 relationship

1.40

 synergy

1.38

Activations Density 0.016%

instances of the word 'interaction'

references to various forms of interaction

No Comments

No Known Activations