INDEX

Explanations

criticisms or negative feedback

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "criticism" 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 @ 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

coat

-0.74

tre

-0.74

ipeg

-0.73

change

-0.69

ston

-0.68

minster

-0.67

 Hurricanes

-0.67

âĢ¢âĢ¢âĢ¢âĢ¢

-0.67

ahon

-0.63

bang

-0.63

POSITIVE LOGITS

 leveled

0.95

ä»£

0.84

 criticism

0.83

 critiques

0.82

 critic

0.79

 harshly

0.78

 criticizing

0.77

 leve

0.76

 levied

0.76

 criticisms

0.76

Activations Density 0.042%

criticisms or negative feedback

occurrences of the word "criticism" and its variations

No Comments

No Known Activations