INDEX

Explanations

direct speech phrases containing the word "said."

oai_token-act-pair · gpt-3.5-turbo

instances of reported speech or quotations

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

Pont

-0.86

tumblr

-0.77

otype

-0.73

Quantity

-0.72

à¦

-0.71

icum

-0.69

NI

-0.67

pee

-0.67

Recipe

-0.67

EMBER

-0.66

POSITIVE LOGITS

 goodbye

0.83

 moreover

0.81

:"

0.76

 furthermore

0.74

 anecd

0.69

 bluntly

0.68

 sarcast

0.66

 secondly

0.65

:]

0.64

 afterwards

0.63

Activations Density 0.216%

direct speech phrases containing the word "said."

instances of reported speech or quotations

No Comments

No Known Activations