INDEX

Explanations

movie titles

oai_token-act-pair · gpt-3.5-turbo

movie titles or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 carbohyd

-0.83

elong

-0.82

 seiz

-0.77

sembly

-0.76

ailability

-0.75

stocks

-0.73

 credential

-0.72

 benches

-0.72

 knowledgeable

-0.72

 tremend

-0.71

POSITIVE LOGITS

 Remastered

1.21

 Trilogy

1.12

 Unch

1.06

 trilogy

1.01

 soundtrack

0.99

 Redux

0.98

 Companion

0.95

 Chronicles

0.92

;;;;;;;;;;;;

0.91

 Volume

0.91

Activations Density 0.235%

movie titles

movie titles or references

No Comments

No Known Activations