INDEX

Explanations

terms related to retroactivity or nostalgia

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

words related to retro style or retroactively modifying something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Parenthood

-0.69

lain

-0.64

 upfront

-0.63

 almonds

-0.63

illary

-0.63

 pores

-0.62

 words

-0.60

Pru

-0.59

 isEnabled

-0.59

 Lies

-0.59

POSITIVE LOGITS

actively

1.60

active

1.52

fitted

1.48

spective

1.44

grade

1.40

fit

1.40

spection

1.27

fitting

1.27

fits

1.24

reflect

1.19

Activations Density 0.029%

terms related to retroactivity or nostalgia

words related to retro style or retroactively modifying something

No Comments

No Known Activations