INDEX

Explanations

self-related terms and concepts

oai_token-act-pair · gpt-3.5-turbo

references to self-identity and self-awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 GOODMAN

-0.75

 Amend

-0.74

 Nights

-0.73

 Slay

-0.72

 Ashe

-0.71

 Horizon

-0.71

 Orchestra

-0.70

Vid

-0.69

 Leap

-0.68

IUM

-0.68

POSITIVE LOGITS

destruct

1.20

 destruct

1.04

conscious

0.96

upload

0.93

 explanatory

0.91

same

0.82

 esteem

0.80

lessly

0.78

 calcul

0.77

contained

0.77

Activations Density 0.016%

self-related terms and concepts

references to self-identity and self-awareness

No Comments

No Known Activations