INDEX

Explanations

comparison and equality operators in programming contexts

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

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

deals

-0.94

è¦ļéĨĴ

-0.86

sburgh

-0.84

sonian

-0.80

rift

-0.75

Ö¼

-0.74

 perspect

-0.72

agall

-0.71

 Depot

-0.71

Â¨

-0.71

POSITIVE LOGITS

irements

0.74

 null

0.71

dden

0.67

 CHRIST

0.67

<=

0.66

 Ares

0.66

pace

0.66

Staff

0.66

==

0.66

 Benedict

0.65

Activations Density 0.080%

comparison and equality operators in programming contexts

No Comments

No Known Activations