INDEX

Explanations

phrases where individuals are reflecting on or imagining experiences and sensations

oai_token-act-pair · gpt-3.5-turbo

expressions related to the experience of feelings and emotions

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

 defic

-0.73

Notable

-0.71

alpha

-0.70

 temper

-0.69

 objections

-0.68

 decisively

-0.67

license

-0.67

 poles

-0.67

 holdings

-0.66

idelines

-0.65

POSITIVE LOGITS

 seeing

0.76

Seeing

0.73

 knowing

0.71

 reconnect

0.70

ãĤ©

0.70

 remembering

0.69

 feeling

0.69

 witnessing

0.68

ovie

0.67

 Sacrifice

0.67

Activations Density 0.711%

phrases where individuals are reflecting on or imagining experiences and sensations

expressions related to the experience of feelings and emotions

No Comments

No Known Activations