INDEX

Explanations

phrases related to protection and defense

oai_token-act-pair · gpt-3.5-turbo

references to protection, security, and safeguarding of individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 onwards

-0.74

sonian

-0.73

 NEWS

-0.64

 Likely

-0.63

 Difficulty

-0.62

 reckoning

-0.59

psy

-0.58

Cart

-0.57

cart

-0.57

 Trouble

-0.56

POSITIVE LOGITS

 integrity

0.94

egu

0.92

yrights

0.91

 confidentiality

0.91

 secrets

0.87

riott

0.86

 dignity

0.84

tnc

0.82

 privacy

0.78

 endangered

0.77

Activations Density 0.198%

phrases related to protection and defense

references to protection, security, and safeguarding of individuals or groups

No Comments

No Known Activations