INDEX

Explanations

terms related to menu items or options

oai_token-act-pair · gpt-3.5-turbo

references to menu items or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Worldwide

-0.78

apy

-0.76

cia

-0.69

tics

-0.69

 Sidd

-0.66

Downloadha

-0.64

 Spit

-0.64

amia

-0.63

thia

-0.62

esville

-0.62

POSITIVE LOGITS

 item

1.19

 items

1.08

 options

0.92

 Items

0.92

Item

0.91

entry

0.90

 choices

0.86

 option

0.83

 entries

0.82

 entry

0.81

Activations Density 0.047%

terms related to menu items or options

references to menu items or options

No Comments

No Known Activations