INDEX

Explanations

phrases related to the writing process, such as improving writing, making connections, and writing drafts faster

oai_token-act-pair · gpt-3.5-turbo

mentions of novel writing and related publishing topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Chaff

-0.96

illance

-0.85

aband

-0.82

wcsstore

-0.80

AMD

-0.79

 Shinra

-0.79

 dstg

-0.79

¬¼

-0.78

 Rept

-0.78

 Customs

-0.76

POSITIVE LOGITS

 writers

1.89

 Writers

1.85

 literary

1.81

 writing

1.79

 Writing

1.77

 manuscript

1.75

Writ

1.72

 novels

1.68

 novelist

1.67

Writing

1.66

Activations Density 0.477%

phrases related to the writing process, such as improving writing, making connections, and writing drafts faster

mentions of novel writing and related publishing topics

No Comments

No Known Activations