INDEX

Explanations

terms related to the word "humor"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "humor" and its variations

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

hips

-0.77

cape

-0.64

 DARK

-0.63

 Franch

-0.63

 EntityItem

-0.61

 Sacrament

-0.61

 flagged

-0.60

"+

-0.60

AVG

-0.60

 minimized

-0.59

POSITIVE LOGITS

pty

1.23

ility

1.14

orously

1.13

ulus

1.11

mus

1.06

mers

1.03

ankind

1.01

ming

1.01

orous

0.97

iliation

0.95

Activations Density 0.027%

terms related to the word "humor"

occurrences of the word "humor" and its variations

No Comments

No Known Activations