INDEX

Explanations

terms related to filtering or filters, particularly in the context of different applications or technologies

oai_token-act-pair · gpt-3.5-turbo

references to filtering processes or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

eanor

-0.81

olars

-0.75

nee

-0.74

lished

-0.71

ciating

-0.70

ington

-0.68

roach

-0.67

arrass

-0.67

ampions

-0.65

ocamp

-0.65

POSITIVE LOGITS

 filters

0.94

 filtering

0.91

 filter

0.89

 Filter

0.89

filter

0.87

 cutoff

0.80

operator

0.79

 sweeps

0.73

Enlarge

0.70

 cleaners

0.70

Activations Density 0.012%

terms related to filtering or filters, particularly in the context of different applications or technologies

references to filtering processes or materials

No Comments

No Known Activations