INDEX

Explanations

expressions related to gratitude and the impact or significance of actions or items

oai_token-act-pair · gpt-3.5-turbo

phrases expressing gratitude and the significance of making a positive impact

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

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

rul

-0.60

thora

-0.60

ãĥ¼ãĥĨãĤ£

-0.59

 Fever

-0.58

 blackout

-0.58

 diction

-0.58

 blat

-0.58

Buk

-0.56

 faint

-0.55

pread

-0.55

POSITIVE LOGITS

 financially

0.98

 economically

0.90

advertising

0.76

 someday

0.76

 compared

0.75

 wonders

0.73

 intangible

0.72

 spiritually

0.71

 psychologically

0.71

 emotionally

0.71

Activations Density 0.250%

expressions related to gratitude and the impact or significance of actions or items

phrases expressing gratitude and the significance of making a positive impact

No Comments

No Known Activations