INDEX

Explanations

words indicating approximation or estimation

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

oli

-0.68

ieu

-0.68

era

-0.68

ves

-0.65

ters

-0.65

woods

-0.64

rive

-0.64

rift

-0.62

 Rebels

-0.62

Express

-0.62

POSITIVE LOGITS

 analogous

0.91

0.86

 WATCHED

0.85

0.84

0.83

0.81

Ĥİ

0.81

Ń·

0.81

 equivalent

0.81

Activations Density 0.031%

words indicating approximation or estimation

No Comments

No Known Activations