INDEX

Explanations

technical terms related to scientific figures and results

oai_token-act-pair · gpt-3.5-turbo

references to figures or illustrations within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

itiz

-0.74

minist

-0.72

ntil

-0.71

erker

-0.71

 homeland

-0.69

sent

-0.67

 polic

-0.67

role

-0.67

mares

-0.66

cycl

-0.65

POSITIVE LOGITS

Figure

1.14

 Figure

0.86

Table

0.82

Fig

0.81

 depicts

0.81

 Exhibit

0.78

 illustrating

0.77

 Drawing

0.76

Fig

0.74

FIG

0.72

Activations Density 0.025%

technical terms related to scientific figures and results

references to figures or illustrations within the document

No Comments

No Known Activations