INDEX

Explanations

references to art, its value, and its influence in society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.3.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.85

:]

-0.72

vati

-0.69

bial

-0.68

owship

-0.65

insula

-0.64

ibaba

-0.64

ociate

-0.64

berger

-0.62

 isot

-0.62

POSITIVE LOGITS

 Parables

0.76

 Genius

0.71

 fetish

0.68

 Quran

0.67

 depicting

0.67

 Circus

0.67

 Logo

0.64

 leaps

0.64

Beast

0.63

Ã©r

0.62

Activations Density 0.373%

references to art, its value, and its influence in society

No Comments

No Known Activations