INDEX

Explanations

words related to filtering or filtration

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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eanor

-0.85

nee

-0.77

olars

-0.73

pered

-0.70

arrass

-0.69

lished

-0.67

ensional

-0.67

erald

-0.67

AAAAAAAA

-0.67

ampions

-0.66

POSITIVE LOGITS

 filters

1.04

 filter

0.98

 filtering

0.96

 Filter

0.93

filter

0.93

 cutoff

0.80

operator

0.77

 cleaners

0.76

Filter

0.73

andom

0.72

Activations Density 0.010%

words related to filtering or filtration

references to filtering processes or materials

No Comments

No Known Activations