INDEX

Explanations

significant phrases indicating introspection or reflection

oai_token-act-pair · gpt-3.5-turbo

references to specific events, times, and contextual details related to history or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NBA

-0.59

 rightfully

-0.58

oÄŁan

-0.56

 Remain

-0.56

 uncond

-0.55

 specifically

-0.55

 unamb

-0.54

leneck

-0.53

 essentially

-0.53

aganda

-0.53

POSITIVE LOGITS

itiz

0.66

 occurs

0.65

 Aires

0.65

tarians

0.64

pires

0.63

 happens

0.62

nces

0.62

ses

0.62

ishes

0.62

WARE

0.61

Activations Density 0.679%

significant phrases indicating introspection or reflection

references to specific events, times, and contextual details related to history or observations

No Comments

No Known Activations