INDEX

Explanations

references to electrical plugs or plug-related actions

oai_token-act-pair · gpt-3.5-turbo

references to "plug-in" technology or devices

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

quez

-0.72

birth

-0.71

perse

-0.68

IAS

-0.66

 Butterfly

-0.65

 surv

-0.63

vict

-0.62

swer

-0.62

 Lann

-0.61

 ACTIONS

-0.61

POSITIVE LOGITS

ging

1.42

ged

1.33

glers

1.22

plug

0.98

 plug

0.95

atis

0.88

 plugs

0.87

lessly

0.85

 Plug

0.83

gers

0.81

Activations Density 0.013%

references to electrical plugs or plug-related actions

references to "plug-in" technology or devices

No Comments

No Known Activations