INDEX

Explanations

mentions of the Indian Prime Minister Narendra Modi

oai_token-act-pair · gpt-3.5-turbo

mentions of the Indian Prime Minister Narendra Modi

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

erness

-0.86

mble

-0.73

 therapists

-0.72

 Cuban

-0.68

Ĥ¬

-0.66

ages

-0.66

 ROCK

-0.65

 therapist

-0.65

 Beir

-0.65

 Wonderland

-0.65

POSITIVE LOGITS

 Modi

1.40

 Sharma

1.12

 Kejriwal

1.10

 Kumar

1.04

 Singh

1.03

 Gandhi

1.03

Rao

1.00

 Gujarat

0.99

jriwal

0.99

 Pradesh

0.96

Activations Density 0.057%

mentions of the Indian Prime Minister Narendra Modi

mentions of the Indian Prime Minister Narendra Modi

No Comments

No Known Activations