INDEX

Explanations

quotations or reported speech

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" 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

 ILCS

-0.74

Lens

-0.72

AMY

-0.71

ï¸ı

-0.69

ICAL

-0.67

ective

-0.67

ãĥĥãĥĪ

-0.65

aspx

-0.64

EDIT

-0.64

patch

-0.63

POSITIVE LOGITS

 sarcast

0.95

 aloud

0.91

 bluntly

0.88

 goodbye

0.84

 Thursday

0.82

 Wednesday

0.82

 apologized

0.82

 forcefully

0.82

 passionately

0.81

 afterward

0.81

Activations Density 0.200%

quotations or reported speech

instances of the word "said" in various contexts

No Comments

No Known Activations