INDEX

Explanations

references to superlatives, particularly indicating the highest degree or extent of something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "one of the" followed by a noun or noun phrase

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

heit

-0.81

ENCE

-0.71

leeve

-0.71

oney

-0.70

SPONSORED

-0.67

fulness

-0.66

Ly

-0.66

LIST

-0.65

govtrack

-0.65

CLE

-0.65

POSITIVE LOGITS

 earliest

1.00

 largest

0.90

 busiest

0.89

 aforementioned

0.89

 strongest

0.89

 highest

0.88

 finest

0.85

 greatest

0.84

ses

0.83

 hardest

0.82

Activations Density 0.127%

references to superlatives, particularly indicating the highest degree or extent of something

instances of the phrase "one of the" followed by a noun or noun phrase

No Comments

No Known Activations