INDEX

Explanations

mentions of the term "narrative"

oai_token-act-pair · gpt-3.5-turbo

mentions of the concept of "narrative."

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

ertodd

-0.95

unte

-0.94

sterdam

-0.91

ateurs

-0.89

ldon

-0.82

ikarp

-0.81

rador

-0.80

urtles

-0.79

enhagen

-0.79

ournaments

-0.78

POSITIVE LOGITS

 narratives

0.90

 arcs

0.86

 narrative

0.80

 portrayal

0.75

arc

0.74

 unfolds

0.74

telling

0.73

 disson

0.73

 Narr

0.71

ãĥ¼ãĥĨ

0.71

Activations Density 0.016%

mentions of the term "narrative"

mentions of the concept of "narrative."

No Comments

No Known Activations