INDEX

Explanations

specific anime titles or related terms

oai_token-act-pair · gpt-3.5-turbo

references to specific movies and characters within the broad context of film and television

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

 spons

-0.84

 Cosponsors

-0.79

hower

-0.77

imentary

-0.76

 benches

-0.76

phasis

-0.75

helps

-0.72

 vested

-0.71

coe

-0.71

spons

-0.70

POSITIVE LOGITS

 Masquerade

0.96

 Legacy

0.91

 Apocalypse

0.90

 Awakening

0.89

 Armageddon

0.87

 sequels

0.87

 Nightmare

0.87

 Kinect

0.86

 Ultimate

0.86

 Deadly

0.85

Activations Density 0.231%

specific anime titles or related terms

references to specific movies and characters within the broad context of film and television

No Comments

No Known Activations