INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

specific years or date ranges mentioned in the text

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

vs

-0.80

-0.73

 princ

-0.73

SourceFile

-0.72

à

-0.70

Sov

-0.64

paralle

-0.62

cow

-0.61

dds

-0.60

cro

-0.59

POSITIVE LOGITS

oulos

0.81

 respectively

0.74

depending

0.70

 inclusive

0.70

isan

0.69

 depending

0.67

enn

0.66

ulse

0.63

 alike

0.63

ennial

0.63

Activations Density 0.110%

dates or time periods

specific years or date ranges mentioned in the text

No Comments

No Known Activations