INDEX

Explanations

phrases related to plot points or storylines

oai_token-act-pair · gpt-3.5-turbo

references to plot elements in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

IDA

-0.75

angelo

-0.73

Downloadha

-0.69

 certify

-0.67

ributed

-0.65

ategory

-0.64

++++++++++++++++

-0.64

KEY

-0.64

iosis

-0.63

ingu

-0.61

POSITIVE LOGITS

 plot

1.22

 plots

1.09

 Plot

1.06

plot

1.00

 plotting

0.97

ories

0.88

Plot

0.88

 synopsis

0.82

lines

0.79

ters

0.77

Activations Density 0.008%

phrases related to plot points or storylines

references to plot elements in narratives

No Comments

No Known Activations