INDEX

Explanations

conjunctions and phrases indicating reasoning or argumentation

oai_token-act-pair · gpt-3.5-turbo

instances of commas or punctuation that suggest complex or multi-part statements

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

asma

-0.80

iple

-0.78

uber

-0.70

rosse

-0.69

atars

-0.68

umen

-0.67

ogly

-0.66

enne

-0.66

hatt

-0.65

chell

-0.65

POSITIVE LOGITS

 namely

1.28

 lest

1.24

 thereby

1.16

 albeit

1.15

channelAvailability

1.08

 whereby

1.05

 insofar

1.05

 though

1.04

 notwithstanding

1.01

 however

0.99

Activations Density 0.451%

conjunctions and phrases indicating reasoning or argumentation

instances of commas or punctuation that suggest complex or multi-part statements

No Comments

No Known Activations