INDEX

Explanations

phrases denoting statements made by individuals, possibly in a position of authority or expertise

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" used in reported speech or quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

otin

-0.80

 ILCS

-0.74

à¦

-0.73

\/\/

-0.71

cffffcc

-0.66

pes

-0.63

ãĥ¥

-0.61

ãģ

-0.60

ãģĨ

-0.60

illions

-0.60

POSITIVE LOGITS

 yesterday

0.77

inery

0.76

terday

0.74

 afterward

0.69

 bluntly

0.69

doms

0.67

 Superintendent

0.65

hement

0.64

ieu

0.64

 earlier

0.63

Activations Density 0.192%

phrases denoting statements made by individuals, possibly in a position of authority or expertise

instances of the word "said" used in reported speech or quotes

No Comments

No Known Activations