INDEX

Explanations

technical terms related to IT and computer operations

oai_token-act-pair · gpt-3.5-turbo

concepts related to deception and false beliefs in social contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Axel

-0.75

 Malk

-0.69

ozyg

-0.65

NIC

-0.64

tein

-0.63

[*

-0.62

itol

-0.61

itialized

-0.61

rique

-0.59

Pog

-0.59

POSITIVE LOGITS

 respectively

1.09

etc

0.79

NetMessage

0.71

 collectively

0.66

 trademarks

0.65

including

0.65

depending

0.64

collect

0.63

 indoors

0.63

often

0.61

Activations Density 1.271%

technical terms related to IT and computer operations

concepts related to deception and false beliefs in social contexts

No Comments

No Known Activations