INDEX

Explanations

safety and security-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to security threats and illegal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sums

-0.56

 CONTR

-0.56

 Factors

-0.55

 Balanced

-0.53

 Donation

-0.53

 Decision

-0.52

 trust

-0.51

amen

-0.51

 Piano

-0.51

 gratitude

-0.51

POSITIVE LOGITS

 abound

1.03

 prolifer

0.98

 rampant

0.98

 everywhere

0.91

 popping

0.91

 bloom

0.89

 lurking

0.84

 prevalent

0.81

 emerge

0.81

 thrive

0.80

Activations Density 1.348%

safety and security-related terms

terms related to security threats and illegal activities

No Comments

No Known Activations