INDEX

Explanations

technical terms related to scientific figures or diagrams

oai_token-act-pair · gpt-3.5-turbo

references to figures or illustrations in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

die

-0.71

ãĥ£

-0.68

 lockout

-0.68

Ì¶

-0.65

campus

-0.64

qua

-0.64

zone

-0.62

thro

-0.62

wcs

-0.61

hate

-0.61

POSITIVE LOGITS

0.93

 below

0.88

Figure

0.86

 Contents

0.85

0.83

Â¶

0.82

0.81

 summarizes

0.80

 Figure

0.80

Activations Density 0.036%

technical terms related to scientific figures or diagrams

references to figures or illustrations in a text

No Comments

No Known Activations