INDEX

Explanations

references to India and Indian entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kessler

-0.82

mble

-0.74

ilts

-0.73

iaries

-0.73

rd

-0.72

esters

-0.72

umbnails

-0.72

 Staten

-0.72

 Jenner

-0.71

yles

-0.70

POSITIVE LOGITS

apolis

1.11

 Pradesh

0.97

 Sharma

0.93

ru

0.92

Rao

0.88

 Kumar

0.88

 Punjab

0.85

endra

0.83

 Singh

0.80

Pv

0.76

Activations Density 0.042%

references to India and Indian entities

No Comments

No Known Activations