INDEX

Explanations

numeric values or identifiers

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

 Hert

-0.91

Nev

-0.76

 Slovakia

-0.74

 Meridian

-0.73

Hua

-0.72

 Luxembourg

-0.71

hend

-0.69

 Irwin

-0.69

 Hemisphere

-0.68

Alc

-0.68

POSITIVE LOGITS

1.43

1.13

ģ

1.02

0.99

0.87

ĭ

0.85

ishops

0.79

0.78

Activations Density 0.071%

numeric values or identifiers

No Comments

No Known Activations