INDEX

Explanations

phrases starting with "Let" followed by interactions or statements

oai_token-act-pair · gpt-3.5-turbo

phrases starting with "Let."

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

atana

-0.72

existent

-0.69

PLIED

-0.68

Zen

-0.65

ÂłÂłÂł

-0.64

 Soldier

-0.64

 holiest

-0.63

natureconservancy

-0.62

ragon

-0.60

 Âł Âł Âł Âł

-0.59

POSITIVE LOGITS

itia

1.06

icia

0.98

tering

0.93

ting

0.93

tered

0.92

hetically

0.71

cheon

0.70

aston

0.69

winter

0.67

ters

0.67

Activations Density 0.017%

phrases starting with "Let" followed by interactions or statements

phrases starting with "Let."

No Comments

No Known Activations