INDEX

Explanations

legal and ethical violations or concerns

oai_token-act-pair · gpt-3.5-turbo

concepts related to legality and ethical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 annot

-0.64

ebted

-0.64

 mock

-0.63

 envelop

-0.61

 hail

-0.60

 annotations

-0.60

 Sloan

-0.58

 diligently

-0.57

 battled

-0.56

 handwritten

-0.56

POSITIVE LOGITS

SPONSORED

0.91

$$$$

0.85

ceivable

0.84

 blasphemy

0.83

 heresy

0.82

brainer

0.77

 deterrent

0.76

advertising

0.76

ausible

0.74

 prohib

0.73

Activations Density 0.728%

legal and ethical violations or concerns

concepts related to legality and ethical issues

No Comments

No Known Activations