INDEX

Explanations

instances where someone is blocked or unblocked on social media platforms like Twitter

oai_token-act-pair · gpt-3.5-turbo

instances of the word "block" and its variations

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

 subp

-0.73

 mortar

-0.64

 warr

-0.63

 vapor

-0.62

 capsule

-0.62

ppa

-0.60

chief

-0.59

 appropri

-0.59

 princ

-0.58

 poster

-0.57

POSITIVE LOGITS

ances

0.97

ables

0.94

enged

0.93

ible

0.89

able

0.87

ãĥ¼ãĤ¯

0.85

hemy

0.83

ers

0.80

ement

0.77

zee

0.76

Activations Density 0.026%

instances where someone is blocked or unblocked on social media platforms like Twitter

instances of the word "block" and its variations

No Comments

No Known Activations