INDEX

Explanations

phrases related to specific movies, TV shows, and actors

oai_token-act-pair · gpt-3.5-turbo

references to specific movies and pop culture elements

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

 submar

-0.78

 appointing

-0.77

 referen

-0.73

umably

-0.71

ibly

-0.70

 defect

-0.70

 declining

-0.69

rower

-0.69

heastern

-0.68

 sponsoring

-0.67

POSITIVE LOGITS

 Circus

1.00

 Nights

0.95

 Deadly

0.95

 Forever

0.94

 Girl

0.93

 Madness

0.93

 Mama

0.91

 Night

0.91

 Kids

0.90

 Secrets

0.90

Activations Density 0.795%

phrases related to specific movies, TV shows, and actors

references to specific movies and pop culture elements

No Comments

No Known Activations