INDEX

Explanations

words related to actions and categorizations

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

awa

-0.97

pora

-0.81

 simultane

-0.74

 ende

-0.72

 mosqu

-0.72

stic

-0.69

 unborn

-0.67

 streng

-0.67

 Niet

-0.65

urated

-0.63

POSITIVE LOGITS

 Consortium

0.80

 Hera

0.78

 Karn

0.73

 Clair

0.67

 Samurai

0.66

Recipe

0.63

éŃĶ

0.62

Shot

0.62

ItemImage

0.62

ULT

0.61

Activations Density 0.028%

words related to actions and categorizations

No Comments

No Known Activations