INDEX

Explanations

mentions of Indian Prime Minister Narendra Modi

oai_token-act-pair · gpt-3.5-turbo

references to the political figure Narendra Modi

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

ngth

-0.78

 CLIENT

-0.78

 Beir

-0.71

retched

-0.69

 Jacksonville

-0.67

ritch

-0.66

AGES

-0.65

ELF

-0.65

 Niet

-0.64

cuts

-0.63

POSITIVE LOGITS

 Modi

0.97

 Jinping

0.82

abad

0.76

Å¡

0.74

 candidacy

0.73

oji

0.73

ji

0.72

etz

0.72

dh

0.72

Äĩ

0.70

Activations Density 0.018%

mentions of Indian Prime Minister Narendra Modi

references to the political figure Narendra Modi

No Comments

No Known Activations