INDEX

Explanations

articles and modifiers related to nouns

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

nces

-0.80

upe

-0.72

itudes

-0.70

aru

-0.66

atism

-0.64

susp

-0.63

fetched

-0.63

ilon

-0.63

olas

-0.62

ãĥīãĥ©

-0.61

POSITIVE LOGITS

illery

0.80

 Panc

0.67

warts

0.66

 singles

0.64

YL

0.62

¬¼

0.61

thren

0.61

belt

0.60

halla

0.59

 Wrestle

0.58

Activations Density 0.276%

articles and modifiers related to nouns

No Comments

No Known Activations