INDEX

Explanations

references to figures in a scientific context

oai_token-act-pair · gpt-3.5-turbo

references to figures and illustrations in a scientific context

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

 inquest

-0.77

 imperson

-0.73

 affairs

-0.71

iscons

-0.70

 grief

-0.68

 deliber

-0.67

 philosophies

-0.66

nesia

-0.66

 educ

-0.65

 philosophy

-0.64

POSITIVE LOGITS

Figure

0.85

 largeDownload

0.80

figure

0.76

 illustrates

0.74

RW

0.74

fig

0.73

 depicts

0.71

 summar

0.69

ħĭ

0.67

 Exhibit

0.67

Activations Density 0.077%

references to figures in a scientific context

references to figures and illustrations in a scientific context

No Comments

No Known Activations