INDEX

Explanations

phrases related to diverse individuals or groups

oai_token-act-pair · gpt-3.5-turbo

phrases referencing people of color

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Enlarge

-0.67

ertodd

-0.63

Features

-0.62

 externalToEVAOnly

-0.60

gallery

-0.59

 Dispatch

-0.58

abre

-0.58

 PowerPoint

-0.58

Examples

-0.57

 Donation

-0.57

POSITIVE LOGITS

sembly

0.89

ortunately

0.85

 whom

0.82

 course

0.80

ief

0.73

icial

0.67

 theirs

0.66

pires

0.64

 justice

0.64

course

0.63

Activations Density 0.140%

phrases related to diverse individuals or groups

phrases referencing people of color

No Comments

No Known Activations