INDEX

Explanations

language related to complex and intertwined situations or relationships

oai_token-act-pair · gpt-3.5-turbo

concepts related to complexity and entanglement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iphate

-0.71

viks

-0.70

udeb

-0.64

/+

-0.63

vation

-0.63

avement

-0.61

Train

-0.61

 Schwarzenegger

-0.61

ablishment

-0.61

inent

-0.61

POSITIVE LOGITS

 intertw

1.00

 intertwined

0.99

 tangled

0.88

 thorn

0.87

 convol

0.87

 entangled

0.85

 knot

0.82

 Afric

0.79

 swirling

0.77

 politic

0.77

Activations Density 0.056%

language related to complex and intertwined situations or relationships

concepts related to complexity and entanglement

No Comments

No Known Activations