INDEX

Explanations

Proper nouns related to finance and industry

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Did" and other auxiliary verbs indicative of actions or inquiries

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

etheless

-0.95

Closure

-0.76

 flare

-0.71

åĳ

-0.70

âĶĢâĶĢ

-0.68

 totality

-0.67

theless

-0.66

 confinement

-0.65

 resemb

-0.64

 reversal

-0.61

POSITIVE LOGITS

ilon

0.94

vas

0.92

avan

0.90

lems

0.88

sell

0.86

ona

0.83

bas

0.82

kel

0.82

linger

0.82

ago

0.82

Activations Density 0.073%

Proper nouns related to finance and industry

the presence of the word "Did" and other auxiliary verbs indicative of actions or inquiries

No Comments

No Known Activations