INDEX

Explanations

phrases related to seeking additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

pex

-0.76

adr

-0.74

ļé

-0.71

xtap

-0.69

©¶æ¥µ

-0.68

²¾

-0.67

ufact

-0.67

ãĥ£

-0.65

 stret

-0.64

hra

-0.62

POSITIVE LOGITS

 Â»

0.94

 âĨĴ

0.88

 VIDEOS

0.85

 than

0.83

...]

0.81

>>

0.77

>>

0.77

 âĢº

0.74

Quotes

0.68

=>

0.67

Activations Density 0.015%

phrases related to seeking additional information

No Comments

No Known Activations