INDEX

Explanations

words that end in 'ly'

oai_token-act-pair · gpt-3.5-turbo

adverbs 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilater

-0.84

irlf

-0.79

eers

-0.77

arians

-0.72

itive

-0.70

ilogy

-0.70

igent

-0.69

 Gutenberg

-0.68

ifully

-0.67

 respectively

-0.66

POSITIVE LOGITS

tics

1.20

rics

1.12

puff

1.11

sis

0.94

pha

0.90

ffe

0.89

phant

0.87

eah

0.85

mph

0.84

rical

0.84

Activations Density 0.044%

words that end in 'ly'

adverbs in various contexts

No Comments

No Known Activations