INDEX

Explanations

parodies or spoofed content

oai_token-act-pair · gpt-3.5-turbo

terms related to parody, spoof, and satire

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

 Dynamics

-0.87

erto

-0.82

frames

-0.75

omen

-0.73

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.71

aining

-0.69

inventoryQuantity

-0.68

 cryst

-0.68

acia

-0.67

å£«

-0.67

POSITIVE LOGITS

 spoof

1.14

netflix

1.06

 parody

1.04

 mockery

1.03

 mocking

1.02

 caric

0.90

 satir

0.90

 caricature

0.89

 imperson

0.85

 joking

0.84

Activations Density 0.044%

parodies or spoofed content

terms related to parody, spoof, and satire

No Comments

No Known Activations