INDEX

Explanations

instances of the word "smoke."

oai_token-act-pair · gpt-3.5-turbo

references to smoke in various contexts

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

 mathematic

-0.68

 Volt

-0.67

HCR

-0.67

":["

-0.65

 reluct

-0.63

 Vanguard

-0.62

*/(

-0.61

UFC

-0.61

 campuses

-0.60

ngth

-0.59

POSITIVE LOGITS

 smoke

1.07

 Smoke

0.94

crow

0.86

 inhal

0.86

lake

0.83

creen

0.82

 haze

0.81

balls

0.80

leaf

0.78

walker

0.78

Activations Density 0.014%

instances of the word "smoke."

references to smoke in various contexts

No Comments

No Known Activations