INDEX

Explanations

phrases indicating events happening in preparation for future occurrences

oai_token-act-pair · gpt-3.5-turbo

references to future events or actions

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

ãĥīãĥ©ãĤ´ãĥ³

-0.80

ASE

-0.75

pmwiki

-0.73

cci

-0.72

ifted

-0.69

izards

-0.69

rug

-0.69

odor

-0.68

Ì¶

-0.68

cu

-0.67

POSITIVE LOGITS

 ahead

0.86

wards

0.82

Ħ¢

0.82

noon

0.78

olicy

0.77

etheless

0.73

dated

0.71

 antioxid

0.70

 awaiting

0.70

manship

0.65

Activations Density 0.008%

phrases indicating events happening in preparation for future occurrences

references to future events or actions

No Comments

No Known Activations