INDEX

Explanations

terms related to a specific fictional series or franchise

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Ap" or its variations in different contexts

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

 Dynamics

-0.69

fast

-0.66

 Instruments

-0.65

 Hurricanes

-0.65

 Lauder

-0.63

 naughty

-0.63

âĶĢâĶĢ

-0.62

enegger

-0.62

 dwar

-0.61

 Jenner

-0.61

POSITIVE LOGITS

artment

1.40

ocaly

1.36

athetic

1.32

ocalyptic

1.31

ocry

1.28

ollo

1.27

athy

1.17

ocalypse

1.16

osit

1.13

alach

1.13

Activations Density 0.024%

terms related to a specific fictional series or franchise

occurrences of the word "Ap" or its variations in different contexts

No Comments

No Known Activations