INDEX

Explanations

words related to active participation or involvement

oai_token-act-pair · gpt-3.5-turbo

the use of the word "actively" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

elf

-0.86

 Chaser

-0.82

 Parables

-0.79

wich

-0.75

esan

-0.73

 Cris

-0.73

 dignity

-0.71

Fine

-0.69

oru

-0.64

 Tycoon

-0.64

POSITIVE LOGITS

 engaged

1.05

 actively

0.95

 solic

0.88

 participated

0.81

 encouraged

0.80

 participates

0.79

 recruited

0.76

uated

0.76

 discouraged

0.75

uates

0.75

Activations Density 0.007%

words related to active participation or involvement

the use of the word "actively" in various contexts

No Comments

No Known Activations