INDEX

Explanations

references to characters in a story or media

oai_token-act-pair · gpt-3.5-turbo

references to characters in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

agles

-0.74

¿½

-0.69

atories

-0.67

yg

-0.66

rup

-0.65

angular

-0.65

sterdam

-0.64

aband

-0.62

obar

-0.62

roxy

-0.61

POSITIVE LOGITS

istically

1.52

izations

1.38

istics

1.37

acters

1.31

isation

1.19

isations

1.18

izes

1.06

 arcs

0.97

arc

0.93

ised

0.93

Activations Density 0.052%

references to characters in a story or media

references to characters in narratives

No Comments

No Known Activations