INDEX

Explanations

instances of importance or significance in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abus

-0.71

worthiness

-0.67

Buzz

-0.67

@@

-0.62

ico

-0.62

 PLEASE

-0.61

WHY

-0.61

OTO

-0.61

}.

-0.60

 Dise

-0.59

POSITIVE LOGITS

 predomin

0.81

 indistinguishable

0.75

omorphic

0.68

 usually

0.67

natureconservancy

0.67

uchs

0.66

ided

0.65

 pitted

0.64

emin

0.64

 traditionally

0.64

Activations Density 0.410%

instances of importance or significance in various contexts

No Comments

No Known Activations