INDEX

Explanations

subtle details or nuances in text

oai_token-act-pair · gpt-3.5-turbo

instances and discussions of subtlety, particularly in various contexts relating to social dynamics and perceptions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

©¶æ

-0.68

 Rising

-0.65

 Cust

-0.65

papers

-0.65

APTER

-0.63

ISO

-0.62

HOME

-0.61

ETF

-0.61

ourced

-0.60

redits

-0.60

POSITIVE LOGITS

ty

1.32

 nuances

0.85

 hints

0.79

 subtle

0.77

aneous

0.77

ener

0.77

 Subtle

0.76

 differences

0.76

ihad

0.76

ures

0.75

Activations Density 0.040%

subtle details or nuances in text

instances and discussions of subtlety, particularly in various contexts relating to social dynamics and perceptions

No Known Activations