INDEX

Explanations

various negative emotions, such as fear, grief, anger, and shame

oai_token-act-pair · gpt-3.5-turbo

references to negative emotions and sentiments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abase

-0.85

ividual

-0.79

ä»£

-0.78

*/(

-0.76

sites

-0.75

 Cosponsors

-0.74

pps

-0.74

annis

-0.72

kas

-0.72

geons

-0.72

POSITIVE LOGITS

 sadness

1.60

 frustration

1.58

 anxiety

1.57

 anger

1.55

 anguish

1.47

 sorrow

1.46

 resentment

1.44

awe

1.42

 disappointment

1.41

 despair

1.41

Activations Density 0.173%

various negative emotions, such as fear, grief, anger, and shame

references to negative emotions and sentiments

No Comments

No Known Activations