INDEX

Explanations

words related to negative emotions, such as fear, anxiety, and frustration

oai_token-act-pair · gpt-3.5-turbo

expressions of emotional distress and psychological states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 arsen

-0.81

soDeliveryDate

-0.75

natureconservancy

-0.73

çīĪ

-0.69

vernment

-0.67

 Unch

-0.64

 backdoor

-0.63

folio

-0.62

è£

-0.62

itures

-0.62

POSITIVE LOGITS

 sadness

0.94

inducing

0.93

 loneliness

0.83

 anguish

0.80

 sorrow

0.79

 feelings

0.79

 disbelief

0.77

 palpable

0.77

 nausea

0.77

 melancholy

0.75

Activations Density 0.513%

words related to negative emotions, such as fear, anxiety, and frustration

expressions of emotional distress and psychological states

No Comments

No Known Activations