INDEX

Explanations

the word "let" followed by a number indicating urgency or priority

oai_token-act-pair · gpt-3.5-turbo

the phrase "let" followed by numerical values indicating commands or suggestions

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

 holiest

-0.74

 Soldier

-0.64

Zen

-0.63

atana

-0.62

PLIED

-0.61

manship

-0.61

oppable

-0.59

 cumbers

-0.59

AGES

-0.58

 vending

-0.57

POSITIVE LOGITS

tered

1.00

tering

0.91

icia

0.82

itia

0.82

ting

0.80

us

0.75

TB

0.66

winter

0.66

cheon

0.65

enne

0.65

Activations Density 0.027%

the word "let" followed by a number indicating urgency or priority

the phrase "let" followed by numerical values indicating commands or suggestions

No Comments

No Known Activations