INDEX

Explanations

phrases related to emotional reactions and decision-making

oai_token-act-pair · gpt-3.5-turbo

verbs related to emotions and negative experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

maxwell

-0.71

peat

-0.70

eworks

-0.70

marine

-0.69

adra

-0.67

paio

-0.67

abin

-0.67

phabet

-0.66

portion

-0.65

"]=>

-0.65

POSITIVE LOGITS

!/

0.62

 retreating

0.62

 Spac

0.61

 inaction

0.61

 exhausted

0.61

 Pitch

0.61

Gim

0.61

 Centauri

0.60

[|

0.59

 exile

0.58

Activations Density 0.181%

phrases related to emotional reactions and decision-making

verbs related to emotions and negative experiences

No Comments

No Known Activations