INDEX

Explanations

technical terms related to network security

oai_token-act-pair · gpt-3.5-turbo

references to a security feature or system, likely relating to SSH or secure shell

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.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

Äĩ

-0.81

 ç¥ŀ

-0.77

ãĥ£

-0.76

enburg

-0.74

 Gamble

-0.71

scene

-0.68

stall

-0.67

addafi

-0.66

 polio

-0.64

whel

-0.63

POSITIVE LOGITS

SS

0.99

HT

0.99

ometimes

0.96

BN

0.88

BM

0.86

yne

0.85

AA

0.84

ELF

0.84

ESSION

0.83

ARS

0.82

Activations Density 0.005%

technical terms related to network security

references to a security feature or system, likely relating to SSH or secure shell

No Comments

No Known Activations