INDEX

Explanations

references to specific years and seasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Beh

-0.71

ersen

-0.64

:{

-0.64

 behavi

-0.63

 Flavoring

-0.63

 VIDEOS

-0.63

 behav

-0.62

 retention

-0.62

 manag

-0.61

 advis

-0.61

POSITIVE LOGITS

0.91

book

0.88

books

0.86

0.85

0.84

0.82

0.81

0.79

Activations Density 0.196%

references to specific years and seasons

No Comments

No Known Activations