INDEX

Explanations

the main characters in a story or narrative

oai_token-act-pair · gpt-3.5-turbo

references to protagonists in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ements

-0.80

assic

-0.78

sterdam

-0.76

dos

-0.73

tx

-0.72

igree

-0.72

namese

-0.70

eln

-0.70

aret

-0.69

redit

-0.69

POSITIVE LOGITS

 protagonist

1.01

 heroine

0.93

acters

0.88

 protagonists

0.87

 Ethan

0.76

 Eleven

0.70

 avatar

0.65

agonist

0.65

 character

0.63

hei

0.63

Activations Density 0.021%

the main characters in a story or narrative

references to protagonists in narratives

No Comments

No Known Activations